research paper poem analysis

Want to create or adapt books like this? Learn more about how Pressbooks supports open publishing practices.

2.6–Sample Analysis of a Poem

R. Paul Cooper

How to Read this Section

This section contains two parts. First, you will find the prompt. The prompt is a very important element in any writing assignment. Don’t be fooled by the fact it is short! Even though it is a short document, it highlights and makes clear every element you will need to complete the given assignment effectively. When writing an essay, the prompt is where you will both begin and end. Seriously. Before you begin, familiarize yourself with the prompt, and before you submit your final draft, give the prompt one final read over, making sure you have not left anything out. When you visit the University Writing Center and Libraries, they can better help if you bring along the prompt. Both the Writing Center [1] and the Libraries [2] provide indispensable tools to aid students, so take advantage of their services.

The second part of this section contains a simulated student essay—the essay is not an actual student essay, but an essay written to demonstrate a strong student essay. The essay in this section is not meant to represent a “perfect” essay; it has its faults. However, this essay is an effective response to the given prompt. The “student” essay will be represented in a wide column on the left, and the grader’s commentary will be represented in a smaller column on the right. Use the example and the comments to help you think about how you might organize your own essay, to think about whether you will make similar—or different—choices.

Sample Prompt

Assignment Description: This essay is a thesis-driven close reading that employs research to add historical, cultural, biographical, or other contextual information. A good thesis is not only original and compelling, but also specific, grounded in fact, and, above all, argumentative. The thesis should also offer the reader a sense of the organization of the essay. As a close reading, this essay will pay more attention to the text itself, effectively skirting any direct scholarship about the given poem in favor of an analysis that focuses on the form and content of a particular poem.

Content: Regarding content, the essay must not stray from the text (so no personal reflections, no political commentary, etc.) Regarding form, the essay should demonstrate a working knowledge of the craft elements of poetry—figurative language, word choice, punctuation, meter, etc. These specific terms can be found in the current version of the OER.

Research Expectations: For research, use less than 3 sources, including the primary source. Secondary sources should be scholarly. We do not expect you to enter into the scholarly conversation around the poem, a facet that will be addressed in later chapters of the OER. For now, it is enough to build up the necessary context, historical or otherwise, to understand the chosen poem. In short, I want to read YOUR well-developed, insightful, and articulate analysis, not someone else’s.

Format: All research should be cited using the current MLA format. The essay as a whole should be formatted in MLA style, and

Scope/Page Count: Should be in the range of 900–1200 words (3–4 pages). A Works Cited page is required.

Attribution:

Cooper, R. Paul. “Poetry: Sample Analysis of a Poem.” In Surface and Subtext: Literature, Research, Writing . 3rd ed. Edited by Claire Carly-Miles, Sarah LeMire, Kathy Christie Anders, Nicole Hagstrom-Schmidt, R. Paul Cooper, and Matt McKinney. College Station: Texas A&M University, 2024. Licensed under a Creative Commons Attribution-NonCommercial 4.0 International License .

Mensah, Korku [pseud.]. “Poetry: ‘One Deathblow’: Claude McKay on Resisting Oppression.” In Surface and Subtext: Literature, Research, Writing . 3rd ed. Edited by Claire Carly-Miles, Sarah LeMire, Kathy Christie Anders, Nicole Hagstrom-Schmidt, R. Paul Cooper, and Matt McKinney. College Station: Texas A&M University, 2024. Licensed under a Creative Commons Attribution-NonCommercial 4.0 International License .

• University Writing Center, Texas A&M University, 2021, https://writingcenter.tamu.edu/. ↵
• Texas A&M University Libraries, Texas A&M University, 2021, https://library.tamu.edu/. ↵

2.6--Sample Analysis of a Poem Copyright © 2024 by R. Paul Cooper is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License , except where otherwise noted.

A Full Guide to Writing a Perfect Poem Analysis Essay

01 October, 2020

14 minutes read

Author:  Elizabeth Brown

Poem analysis is one of the most complicated essay types. It requires the utmost creativity and dedication. Even those who regularly attend a literary class and have enough experience in poem analysis essay elaboration may face considerable difficulties while dealing with the particular poem. The given article aims to provide the detailed guidelines on how to write a poem analysis, elucidate the main principles of writing the essay of the given type, and share with you the handy tips that will help you get the highest score for your poetry analysis. In addition to developing analysis skills, you would be able to take advantage of the poetry analysis essay example to base your poetry analysis essay on, as well as learn how to find a way out in case you have no motivation and your creative assignment must be presented on time.

What Is a Poetry Analysis Essay?

A poetry analysis essay is a type of creative write-up that implies reviewing a poem from different perspectives by dealing with its structural, artistic, and functional pieces. Since the poetry expresses very complicated feelings that may have different meanings depending on the backgrounds of both author and reader, it would not be enough just to focus on the text of the poem you are going to analyze. Poetry has a lot more complex structure and cannot be considered without its special rhythm, images, as well as implied and obvious sense.

While analyzing the poem, the students need to do in-depth research as to its content, taking into account the effect the poetry has or may have on the readers.

Preparing for the Poetry Analysis Writing

The process of preparation for the poem analysis essay writing is almost as important as writing itself. Without completing these stages, you may be at risk of failing your creative assignment. Learn them carefully to remember once and for good.

Thoroughly read the poem several times

The rereading of the poem assigned for analysis will help to catch its concepts and ideas. You will have a possibility to define the rhythm of the poem, its type, and list the techniques applied by the author.

While identifying the type of the poem, you need to define whether you are dealing with:

• Lyric poem – the one that elucidates feelings, experiences, and the emotional state of the author. It is usually short and doesn’t contain any narration;
• Limerick – consists of 5 lines, the first, second, and fifth of which rhyme with one another;
• Sonnet – a poem consisting of 14 lines characterized by an iambic pentameter. William Shakespeare wrote sonnets which have made him famous;
• Ode – 10-line poem aimed at praising someone or something;
• Haiku – a short 3-line poem originated from Japan. It reflects the deep sense hidden behind the ordinary phenomena and events of the physical world;
• Free-verse – poetry with no rhyme.

The type of the poem usually affects its structure and content, so it is important to be aware of all the recognized kinds to set a proper beginning to your poetry analysis.

Find out more about the poem background

Find as much information as possible about the author of the poem, the cultural background of the period it was written in, preludes to its creation, etc. All these data will help you get a better understanding of the poem’s sense and explain much to you in terms of the concepts the poem contains.

Define a subject matter of the poem

This is one of the most challenging tasks since as a rule, the subject matter of the poem isn’t clearly stated by the poets. They don’t want the readers to know immediately what their piece of writing is about and suggest everyone find something different between the lines.

What is the subject matter? In a nutshell, it is the main idea of the poem. Usually, a poem may have a couple of subjects, that is why it is important to list each of them.

In order to correctly identify the goals of a definite poem, you would need to dive into the in-depth research.

Check the historical background of the poetry. The author might have been inspired to write a poem based on some events that occurred in those times or people he met. The lines you analyze may be generated by his reaction to some epoch events. All this information can be easily found online.

Choose poem theories you will support

In the variety of ideas the poem may convey, it is important to stick to only several most important messages you think the author wanted to share with the readers. Each of the listed ideas must be supported by the corresponding evidence as proof of your opinion.

The poetry analysis essay format allows elaborating on several theses that have the most value and weight. Try to build your writing not only on the pure facts that are obvious from the context but also your emotions and feelings the analyzed lines provoke in you.

How to Choose a Poem to Analyze?

If you are free to choose the piece of writing you will base your poem analysis essay on, it is better to select the one you are already familiar with. This may be your favorite poem or one that you have read and analyzed before. In case you face difficulties choosing the subject area of a particular poem, then the best way will be to focus on the idea you feel most confident about. In such a way, you would be able to elaborate on the topic and describe it more precisely.

Now, when you are familiar with the notion of the poetry analysis essay, it’s high time to proceed to poem analysis essay outline. Follow the steps mentioned below to ensure a brilliant structure to your creative assignment.

Best Poem Analysis Essay Topics

• Mother To Son Poem Analysis
• We Real Cool Poem Analysis
• Invictus Poem Analysis
• Richard Cory Poem Analysis
• Ozymandias Poem Analysis
• Barbie Doll Poem Analysis
• Caged Bird Poem Analysis
• Ulysses Poem Analysis
• Dover Beach Poem Analysis
• Annabelle Lee Poem Analysis
• Daddy Poem Analysis
• The Raven Poem Analysis
• The Second Coming Poem Analysis
• Still I Rise Poem Analysis
• If Poem Analysis
• Fire And Ice Poem Analysis
• My Papa’S Waltz Poem Analysis
• Harlem Poem Analysis
• Kubla Khan Poem Analysis
• I Too Poem Analysis
• The Juggler Poem Analysis
• The Fish Poem Analysis
• Jabberwocky Poem Analysis
• Charge Of The Light Brigade Poem Analysis
• The Road Not Taken Poem Analysis
• Landscape With The Fall Of Icarus Poem Analysis
• The History Teacher Poem Analysis
• One Art Poem Analysis
• The Wanderer Poem Analysis
• We Wear The Mask Poem Analysis
• There Will Come Soft Rains Poem Analysis
• Digging Poem Analysis
• The Highwayman Poem Analysis
• The Tyger Poem Analysis
• London Poem Analysis
• Sympathy Poem Analysis
• I Am Joaquin Poem Analysis
• This Is Just To Say Poem Analysis
• Sex Without Love Poem Analysis
• Strange Fruit Poem Analysis
• Dulce Et Decorum Est Poem Analysis
• Emily Dickinson Poem Analysis
• The Flea Poem Analysis
• The Lamb Poem Analysis
• Do Not Go Gentle Into That Good Night Poem Analysis
• My Last Duchess Poetry Analysis

Poem Analysis Essay Outline

As has already been stated, a poetry analysis essay is considered one of the most challenging tasks for the students. Despite the difficulties you may face while dealing with it, the structure of the given type of essay is quite simple. It consists of the introduction, body paragraphs, and the conclusion. In order to get a better understanding of the poem analysis essay structure, check the brief guidelines below.

Introduction

This will be the first section of your essay. The main purpose of the introductory paragraph is to give a reader an idea of what the essay is about and what theses it conveys. The introduction should start with the title of the essay and end with the thesis statement.

The main goal of the introduction is to make readers feel intrigued about the whole concept of the essay and serve as a hook to grab their attention. Include some interesting information about the author, the historical background of the poem, some poem trivia, etc. There is no need to make the introduction too extensive. On the contrary, it should be brief and logical.

Body Paragraphs

The body section should form the main part of poetry analysis. Make sure you have determined a clear focus for your analysis and are ready to elaborate on the main message and meaning of the poem. Mention the tone of the poetry, its speaker, try to describe the recipient of the poem’s idea. Don’t forget to identify the poetic devices and language the author uses to reach the main goals. Describe the imagery and symbolism of the poem, its sound and rhythm.

Try not to stick to too many ideas in your body section, since it may make your essay difficult to understand and too chaotic to perceive. Generalization, however, is also not welcomed. Try to be specific in the description of your perspective.

Make sure the transitions between your paragraphs are smooth and logical to make your essay flow coherent and easy to catch.

In a nutshell, the essay conclusion is a paraphrased thesis statement. Mention it again but in different words to remind the readers of the main purpose of your essay. Sum up the key claims and stress the most important information. The conclusion cannot contain any new ideas and should be used to create a strong impact on the reader. This is your last chance to share your opinion with the audience and convince them your essay is worth readers’ attention.

Problems with writing Your Poem Analysis Essay? Try our Essay Writer Service!

Poem Analysis Essay Examples 

A good poem analysis essay example may serve as a real magic wand to your creative assignment. You may take a look at the structure the other essay authors have used, follow their tone, and get a great share of inspiration and motivation.

Check several poetry analysis essay examples that may be of great assistance:

• https://study.com/academy/lesson/poetry-analysis-essay-example-for-english-literature.html
• https://www.slideshare.net/mariefincher/poetry-analysis-essay

Writing Tips for a Poetry Analysis Essay

If you read carefully all the instructions on how to write a poetry analysis essay provided above, you have probably realized that this is not the easiest assignment on Earth. However, you cannot fail and should try your best to present a brilliant essay to get the highest score. To make your life even easier, check these handy tips on how to analysis poetry with a few little steps.

• In case you have a chance to choose a poem for analysis by yourself, try to focus on one you are familiar with, you are interested in, or your favorite one. The writing process will be smooth and easy in case you are working on the task you truly enjoy.
• Before you proceed to the analysis itself, read the poem out loud to your colleague or just to yourself. It will help you find out some hidden details and senses that may result in new ideas.
• Always check the meaning of words you don’t know. Poetry is quite a tricky phenomenon where a single word or phrase can completely change the meaning of the whole piece. 
• Bother to double check if the conclusion of your essay is based on a single idea and is logically linked to the main body. Such an approach will demonstrate your certain focus and clearly elucidate your views. 
• Read between the lines. Poetry is about senses and emotions – it rarely contains one clearly stated subject matter. Describe the hidden meanings and mention the feelings this has provoked in you. Try to elaborate a full picture that would be based on what is said and what is meant.

Write a Poetry Analysis Essay with HandmadeWriting

You may have hundreds of reasons why you can’t write a brilliant poem analysis essay. In addition to the fact that it is one of the most complicated creative assignments, you can have some personal issues. It can be anything from lots of homework, a part-time job, personal problems, lack of time, or just the absence of motivation. In any case, your main task is not to let all these factors influence your reputation and grades. A perfect way out may be asking the real pros of essay writing for professional help.

There are a lot of benefits why you should refer to the professional writing agencies in case you are not in the mood for elaborating your poetry analysis essay. We will only state the most important ones:

• You can be 100% sure your poem analysis essay will be completed brilliantly. All the research processes, outlines, structuring, editing, and proofreading will be performed instead of you. 
• You will get an absolutely unique plagiarism-free piece of writing that deserves the highest score.
• All the authors are extremely creative, talented, and simply in love with poetry. Just tell them what poetry you would like to build your analysis on and enjoy a smooth essay with the logical structure and amazing content.
• Formatting will be done professionally and without any effort from your side. No need to waste your time on such a boring activity.

As you see, there are a lot of advantages to ordering your poetry analysis essay from HandmadeWriting . Having such a perfect essay example now will contribute to your inspiration and professional growth in future.

A life lesson in Romeo and Juliet taught by death

Due to human nature, we draw conclusions only when life gives us a lesson since the experience of others is not so effective and powerful. Therefore, when analyzing and sorting out common problems we face, we may trace a parallel with well-known book characters or real historical figures. Moreover, we often compare our situations with […]

Ethical Research Paper Topics

Writing a research paper on ethics is not an easy task, especially if you do not possess excellent writing skills and do not like to contemplate controversial questions. But an ethics course is obligatory in all higher education institutions, and students have to look for a way out and be creative. When you find an […]

Art Research Paper Topics

Students obtaining degrees in fine art and art & design programs most commonly need to write a paper on art topics. However, this subject is becoming more popular in educational institutions for expanding students’ horizons. Thus, both groups of receivers of education: those who are into arts and those who only get acquainted with art […]

EH -- Researching Poems: Strategies for Poetry Research

• Find Articles
• Strategies for Poetry Research

Page Overview

This page addresses the research process -- the things that should be done before the actual writing of the paper -- and strategies for engaging in the process.  Although this LibGuide focuses on researching poems or poetry, this particular page is more general in scope and is applicable to most lower-division college research assignments.

Before You Begin

Before beginning any research process, first be absolutely sure you know the requirements of the assignment.  Things such as  

• the date the completed project is due 
• the due dates of any intermediate assignments, like turning in a working bibliography or notes
• the length requirement (minimum word count), if any 
• the minimum number and types (for example, books or articles from scholarly, peer-reviewed journals) of sources required

These formal requirements are as much a part of the assignment as the paper itself.  They form the box into which you must fit your work.  Do not take them lightly.

When possible, it is helpful to subdivide the overall research process into phases, a tactic which

• makes the idea of research less intimidating because you are dealing with sections at a time rather than the whole process
• makes the process easier to manage
• gives a sense of accomplishment as you move from one phase to the next

Characteristics of a Well-written Paper

Although there are many details that must be given attention in writing a research paper, there are three major criteria which must be met.  A well-written paper is

• Unified:  the paper has only one major idea; or, if it seeks to address multiple points, one point is given priority and the others are subordinated to it.
• Coherent: the body of the paper presents its contents in a logical order easy for readers to follow; use of transitional phrases (in addition, because of this, therefore, etc.) between paragraphs and sentences is important.
• Complete:  the paper delivers on everything it promises and does not leave questions in the mind of the reader; everything mentioned in the introduction is discussed somewhere in the paper; the conclusion does not introduce new ideas or anything not already addressed in the paper.

Basic Research Strategy

• How to Research From Pellissippi State Community College Libraries: discusses the principal components of a simple search strategy.
• Basic Research Strategies From Nassau Community College: a start-up guide for college level research that supplements the information in the preceding link. Tabs two, three, and four plus the Web Evaluation tab are the most useful for JSU students. As with any LibGuide originating from another campus, care must be taken to recognize the information which is applicable generally from that which applies solely to the Guide's home campus. .
• Information Literacy Tutorial From Nassau Community College: an elaboration on the material covered in the preceding link (also from NCC) which discusses that material in greater depth. The quizzes and surveys may be ignored.

Things to Keep in Mind

Although a research assignment can be daunting, there are things which can make the process less stressful, more manageable, and yield a better result.  And they are generally applicable across all types and levels of research.

1.  Be aware of the parameters of the assignment: topic selection options, due date, length requirement, source requirements.  These form the box into which you must fit your work.  

2. Treat the assignment as a series of components or stages rather than one undivided whole.

• devise a schedule for each task in the process: topic selection and refinement (background/overview information), source material from books (JaxCat), source material from journals (databases/Discovery), other sources (internet, interviews, non-print materials); the note-taking, drafting, and editing processes.
• stick to your timetable.  Time can be on your side as a researcher, but only if you keep to your schedule and do not delay or put everything off until just before the assignment deadline. 

3.  Leave enough time between your final draft and the submission date of your work that you can do one final proofread after the paper is no longer "fresh" to you.  You may find passages that need additional work because you see that what is on the page and what you meant to write are quite different.  Even better, have a friend or classmate read your final draft before you submit it.  A fresh pair of eyes sometimes has clearer vision. 

4.  If at any point in the process you encounter difficulties, consult a librarian.  Hunters use guides; fishermen use guides.  Explorers use guides.  When you are doing research, you are an explorer in the realm of ideas; your librarian is your guide. 

A Note on Sources

Research requires engagement with various types of sources.

• Primary sources: the thing itself, such as letters, diaries, documents, a painting, a sculpture; in lower-division literary research, usually a play, poem, or short story.
• Secondary sources: information about the primary source, such as books, essays, journal articles, although images and other media also might be included.  Companions, dictionaries, and encyclopedias are secondary sources.
• Tertiary sources: things such as bibliographies, indexes, or electronic databases (minus the full text) which serve as guides to point researchers toward secondary sources.  A full text database would be a combination of a secondary and tertiary source; some books have a bibliography of additional sources in the back.

Accessing sources requires going through various "information portals," each designed to principally support a certain type of content.  Houston Cole Library provides four principal information portals:

• JaxCat online catalog: books, although other items such as journals, newspapers, DVDs, and musical scores also may be searched for.
• Electronic databases: journal articles, newspaper stories, interviews, reviews (and a few books; JaxCat still should be the "go-to" portal for books).  JaxCat indexes records for the complete item: the book, journal, newspaper, CD but has no records for parts of the complete item: the article in the journal, the editorial in the newspaper, the song off the CD.  Databases contain records for these things.
• Discovery Search: mostly journal articles, but also (some) books and (some) random internet pages.  Discovery combines elements of the other three information portals and is especially useful for searches where one is researching a new or obscure topic about which little is likely to be written, or does not know where the desired information may be concentrated.  Discovery is the only portal which permits simul-searching across databases provided by multiple vendors.
• Internet (Bing, Dogpile, DuckDuckGo, Google, etc.): primarily webpages, especially for businesses (.com), government divisions at all levels (.gov), or organizations (.org). as well as pages for primary source-type documents such as lesson plans and public-domain books.  While book content (Google Books) and journal articles (Google Scholar) are accessible, these are not the strengths of the internet and more successful searches for this type of content can be performed through JaxCat and the databases.  

NOTE: There is no predetermined hierarchy among these information portals as regards which one should be used most or gone to first.  These considerations depend on the task at hand and will vary from assignment o assignment.

The link below provides further information on the different source types.

• Research Methods From Truckee Meadows Community College: a guide to basic research. The tab "What Type of Source?" presents an overview of the various types of information sources, identifying the advantages and disadvantages of each.
• << Previous: Find Books
• Last Updated: Nov 8, 2023 1:49 PM
• URL: https://libguides.jsu.edu/litresearchpoems

How to Write a Poem Analysis: 6 Steps for Students and New Reviewers

Elliot Riley

Emily Butler is a librarian and writer. You can discover more of their literary opinions on their YouTube channel, youtube.com/emilybutler, and follow them on Twitter @EmilyFButler1.

View All posts by Elliot Riley

If you’re a student or new reviewer first approaching the task, you may be wondering how to write a poem analysis. Fortunately, there are concrete steps you can take to analyze a poem or collection of poetry. Even if you do not plan on learning how to write a poem analysis essay, building a routine of analysis into your poetry reading can deepen your appreciation for the genre.

Poems have many layers of meaning. A particularly beautiful and well-crafted poem only becomes more enjoyable the more you increase your understanding of the decisions the poet made to craft it. The following steps outline the kinds of questions to ask yourself while writing a poem analysis.

Step 1: Read the Poem Aloud

Poetry has a long oral history. Poets often utilize sound techniques which are easier to detect when reading the poem aloud. Read it once without an analytical focus. Simply notice how you respond to the poem. Begin by asking yourself broad, simple questions such as: How did this make me feel? What do I think the poet is trying to say?

Jot some notes down about your initial impression. Analyzing a poem is a recursive process. You will read the poem several times, and these first impressions can provide interesting clues for what to focus on in your analysis.

Step 2: Identify the Type of Poem

There are several different types of poems, but all poems fall into three overarching categories: free verse, formal verse, and prose poems. Formal poetry itself comes in many more specific forms. Check out A Beginner’s Guide to Different Types of Poems.

There are certain analytical questions you can ask yourself depending on the type of the poem you’re reading. If this is a prose poem, ask yourself, what exactly makes this piece of writing a poem, as opposed to a short piece of prose? Recognizing a specific poetic form allows you to contextualize the poem in history. For example, if you’re reading a sonnet, consider how the poem you’re analyzing fits with or fights against the conventions of sonnets.

Step 3: Mark It Up

There is no one correct way to mark up a poem. You can underline lines which stand out to you. You can take notes in the margins identifying poetic techniques as you see them. You can scan the poem,  a method of marking stressed and unstressed syllables. You can circle words which seem important or stand out as surprising.

If you are reviewing an entire poetry collection, it’s a good idea to take notes in the margins about particular motifs or themes. That way, when you are finished with your first read, you can look for ideas which appeared in multiple poems.

Step 4: Consider Poetic Techniques

Read the poem several times, considering a single poetic technique at a time. For example, free verse and formal poems use line breaks. Read through the poem once, focusing on how the poet has broken lines, and the impact of those decisions. If the poem contains stanzas, do the same for stanzas. You can repeat this process with any poetic technique: similes, metaphors, imagery, assonance, consonance, alliteration. How do these poetic techniques support, enhance, or problematize the overall message of the poem? Your observations will prove crucial when you are ready to sit down and write a poem analysis.

Step 5: Pay Attention to the Turn(s)

In poetry, the term “volta,” sometimes called a “turn,” is a shift in the tone, meaning, or style of a poem. This is a common enough poetic technique that it warrants its own step in the analytic process. Nearly every sonnet contains a turn in the final two lines of the poem, but countless other types of poems contain some sort of shift.

Voltas are so common that if the poem you’re reading does not contain a volta, that is a decision worth incorporating into a poem analysis. You can always ask yourself whether or not a poem contains a turn, and how this impacts the poem overall. Focus on the final lines of a poem, since that is where the volta typically appears.

Step 6: Make an Argument

If you are reviewing an entire poetry collection you can use the above steps for each poem. Then consider the way that the poet has chosen to order the poems within the collection. Revisit the first and last poems, asking yourself how they might function as a kind of introduction and conclusion to the collection.

As with any other essay in the realm of literature, in order to write a poem analysis essay, you should formulate an argument and back it up with evidence. Different readers can have opposing ideas about how a poem or collection of poetry operates, and that’s okay, as long as both readers have evidence to support their claims. How do you back up your claims with evidence? Refer to your notes, especially your observations of poetic techniques. Whenever necessary, quote exact lines or stanzas and use them to support your argument.

Step 7: Consider the Audience

Writing a book review of a poetry collection is considerably different from writing an essay about it. That is because book reviews serve a different purpose than essays do. Individual readers, book buyers, and librarians read reviews in order to decide whether or not to purchase a book.

Ask yourself: what kind of reader might enjoy this collection? It’s always a good idea to compare and contrast to other collections of poetry. You can recommend the poetry collection you’re reviewing to fans of another poet, for example.

Book reviews tend to be considerably shorter than essays, often as short as two or three hundred words. For that reason, it’s important to be concise. Unlike reviewing fiction or nonfiction, you do not exactly need to “summarize” a poetry collection. Most poetry collections cannot be summarized the way that a novel or nonfiction book can. Instead, list some of the central thematic concerns of the collection and describe the poetic style. Tell your readers what kind of poems they will find in this collection. Are these prose poems, free verse, formal verse, or a combination? Are they simple, accessible poems, or complex poems with unusual syntax? Does the collection contain a lot of references?

In a book review, you will want to quote a line or two which represents some aspect of the poetry collection as a whole. Since you do not have a lot of space, choose something representative of the poet’s style. This will give readers an idea of whether or not this collection appeals to them. For more information about writing book reviews, check out How To Write a Book Review: Six Steps to Take .

You Might Also Like

How to Analyze a Poem Like a Pro

Students often analyze poems as part of their literature studies to develop critical thinking skills and deepen their understanding of language and symbolism. Also, to appreciate the nuances of literary expression. Through poetry analysis, students learn to decipher complex themes, understand various literary devices, and explore the emotional and intellectual depth conveyed by poets.

The  professional research paper writers  suggest that students should focus on these key elements for effectively analyzing a poem:

• Literary Devices

Structure and Form

• Theme and Tone

Contextual Understanding

Don’t fret as this comprehensive guide aims to equip students with the necessary tools and insights so they don’t have to wonder how to analyze a poem in an essay again.

Table of Contents

What is a Poem?

A poem is a form of literary expression that employs rhythmic, structured language to evoke emotions, convey ideas, or narrate stories. It’s characterized by its condensed and imaginative use of words, often employing various literary devices and techniques to create vivid imagery and evoke profound feelings in the reader.

Writing a poem involves the delicate craft of arranging words, sounds, and rhythms to evoke emotions or paint a vivid picture. Poets often use figurative language, such as metaphors, similes, and imagery, to convey complex emotions or ideas in a condensed form. The choice of poetic structure, rhyme scheme, and meter contributes to the poem’s overall impact, allowing for a variety of styles and forms of expression.

Elements of a Poem

Key elements of a poem include:

Vivid descriptions that appeal to the senses. Like creating mental pictures for the reader.

Rhyme and Rhythm

Patterns of sounds that enhance the musicality and flow of the poem.

The arrangement of lines, stanzas, and overall organization, that are contributing to the poem’s aesthetic and impact.

Figurative Language

Metaphors, similes, personification, and other devices that add depth and layers of meaning.

Theme and Emotion

Central ideas or emotions conveyed through the poem are often interwoven with the poet’s perspective or experiences.

Students might opt for a  paper writing service  to analyze a poem due to the intricacies involved in understanding poetic devices, structure, and underlying meanings. These services offer expert guidance in deciphering complex literary elements, interpreting symbolism, and analyzing the thematic nuances within a poem.

Common Problems a Student Faces While Analyzing a Poem

Students often encounter several challenges when analyzing a poem:

Complexity of Language and Imagery

Poetic language can be intricate, employing metaphors, symbolism, and figurative devices that require deciphering. Understanding these devices and their intended meaning can be challenging, especially for students new to analyzing poetry.

Interpreting Ambiguity

Poems often possess multiple layers of meaning or ambiguity, making it difficult for students to interpret the poet’s intentions accurately. This ambiguity might lead to varying interpretations, confusing the poem’s central theme or message.

Structural Complexity

Poems come in various forms and structures, such as sonnets, free verse, or ballads, each with its unique patterns and rules. Decoding these structures and their impact on the poem’s meaning can be daunting for students.

Historical, cultural, or biographical context often influences a poem’s meaning. Lacking knowledge of these contexts might hinder students from fully grasping the intended message or significance behind certain references within the poem.

Subjectivity in Analysis

Poetry analysis involves personal interpretation, and there’s often no definitive “right” answer. Students may struggle to articulate their interpretations coherently, leading to uncertainty about their analysis’ accuracy or depth.

10 Top Tips on How to Analyze a Poem

Here’s your answer to how to read a poem or how to analyze one effectively.

Tip 1) Read Multiple Times

Read the poem several times to grasp its nuances. Pay attention to the overall impression, emotions evoked, and any recurring themes or symbols.

Tip 2) Understand Form and Structure

Analyze the poem’s structure, such as rhyme scheme, meter, stanza organization, and line length. Consider how these elements contribute to the poem’s rhythm and meaning.

Tip3) Identify Literary Devices

Spot and analyze literary devices like metaphors, similes, personification, and imagery. Understand how these devices enhance the poem’s depth and convey the poet’s message.

Tip 4) Evaluate Tone and Mood

Consider the emotional tone and mood of the poem. Is it melancholic, hopeful, or reflective? Analyze how the poet’s language choices contribute to these aspects.

Tip 5) Contextualize the Poem

Consider the historical, cultural, or biographical context surrounding the poem’s creation. Understanding the context can illuminate the poet’s intentions and thematic choices.

Tip 6) Analyze Themes and Symbols

Identify the central themes and symbols within the poem. Consider what these elements represent and how they contribute to the overall message or narrative.

Tip 7) Consider the Speaker and Audience

Analyze the perspective of the speaker in the poem and the intended audience. Reflect on how these factors influence the poem’s meaning and impact.

Tip 8) Note Personal Response

Pay attention to your response to the poem. Poetry often evokes subjective emotions, and your interpretation matters in understanding the poem’s depth.

Tip 9) Research and Discuss

Engage in discussions with peers or research further to gain different perspectives and interpretations. Exploring diverse viewpoints can enrich your analysis.

Tip 10) Craft a Detailed Analysis

Synthesize your observations into a cohesive analysis. Structure your analysis by discussing various elements and how they collectively contribute to the poem’s meaning and impact.

Interestingly, a student might be asked to analyze a poem in a short essay, which could be challenging but a  guide on the short essay format  and these pro tips will surely help.

How Can Students Get Better at Analysing a Poem

The professional writers suggest that students can enhance their skills in analyzing poetry through several methods:

Read Diverse Poems

Explore a variety of poems across different eras, styles, and cultures. Exposure to diverse poetry broadens perspectives and introduces various literary techniques and themes.

Analyze Actively

Engage in active reading by annotating poems. Highlight literary devices, note emotions evoked, and mark areas that seem significant or puzzling. This practice aids in deeper comprehension.

Understand Literary Devices

Familiarize yourself with common literary devices like metaphors, similes, imagery, alliteration, and symbolism. Recognizing these devices helps uncover layers of meaning within a poem.

Contextual Research

Dive into the historical, cultural, or biographical context surrounding the poem. Understanding the context provides valuable insights into the poet’s intentions and thematic choices.

Discuss and Collaborate

Engage in discussions with peers or join study groups to share interpretations and gain different viewpoints. Exploring diverse perspectives enhances understanding and critical thinking.

Seek Guidance

Consult teachers, professors, or online resources for guidance. Seeking feedback and discussing interpretations with mentors helps refine analytical skills.

Practice Writing Analyses

Regularly practice writing poetry analysis. Start with simpler poems and gradually progress to more complex ones. Constructing coherent analyses hones analytical skills and improves articulation.

Attend Workshops or Seminars

Participate in workshops or seminars focused on poetry analysis. These events often offer insights from experts and provide practical tips for effective analysis.

Reflect and Revise

After analyzing a poem, reflect on your interpretation. Revisit your analysis, consider alternative viewpoints, and revise your analysis accordingly. This process enhances critical thinking and depth of understanding.

Cultivate Patience and Perseverance

Analyzing poetry is a gradual process that requires patience and perseverance. Keep practicing, exploring, and refining your skills to progressively become more adept at analyzing poems.

Final Thoughts

Understanding poems takes time and a curious mind. This guide gives great tips for figuring out what poems mean. Remember, it’s not just about finding hidden messages, but it’s also about enjoying the language and thinking about what it means to you.

When you’re looking at a poem, take your time. Try to understand how it’s put together and what the poet might be trying to say. Practice makes perfect, so keep trying, and don’t worry if it’s tricky at first.

Our  essay writing service  is here to help if you find it hard to analyze the poem in an essay. Or you would like to read how to analyze a poem example.

Order Original Papers & Essays

Your First Custom Paper Sample is on Us!

Timely Deliveries

No Plagiarism & AI

100% Refund

Try Our Free Paper Writing Service

Related blogs.

Connections with Writers and support

Privacy and Confidentiality Guarantee

Average Quality Score

Academia.edu no longer supports Internet Explorer.

To browse Academia.edu and the wider internet faster and more securely, please take a few seconds to  upgrade your browser .

•  We're Hiring!
•  Help Center

Poetry Analysis

• Most Cited Papers
• Most Downloaded Papers
• Newest Papers
• Save to Library
• Last »
• Economic Policy Evaluation Follow Following
• Nazism Follow Following
• Angela Carter Follow Following
• Gothic Studies Follow Following
• Victorian poetry Follow Following
• Nazi Germany Follow Following
• Gothic Follow Following
• Posmodernism Follow Following
• Gothic Literature Follow Following
• Character Analysis Follow Following

Enter the email address you signed up with and we'll email you a reset link.

• Academia.edu Publishing
•   We're Hiring!
•   Help Center
• Find new research papers in:
• Health Sciences
• Earth Sciences
• Cognitive Science
• Mathematics
• Computer Science
• Academia ©2024

Poetry & Poets

Explore the beauty of poetry – discover the poet within

How To Write A Poetry Research Paper

Introduction

Writing a poetry research paper can be an intimidating task for students. Even for experienced writers, the process of writing a research paper on poetry can be daunting. However, there are a few helpful tips and guidelines that can help make the process easier. Writing a research paper on poetry requires the student to have an analytical understanding of the poet or poet’s work and to utilize multiple sources of evidence in order to make a convincing argument. Before starting the research paper, it is important to properly analyze the poem and to understand the form, structure, and language of the poem.

The process of writing a research paper requires numerous steps, beginning with researching the poet and poem. If a poet is unknown, the research process must be started by learning about their biography, other works, and their impact on society. With online databases, libraries, and archives the research process can move quickly. It is important to carefully document sources for later use when creating bibliographies for the paper. Once the process of researching the poem has been completed, the next step is to analyze the poem itself. It is important for the student to read the poem carefully in order to understand the meaning, as well as its tone, imagery, and metaphors. Furthermore, analyzing other poems by the same poet can help students observe patterns, trends, or elements of a poet’s work.

Outlining and Structure

Outlining the research paper is just as important as analyzing the poem itself. Many students make the mistake of not taking enough time to craft a detailed outline that follows the structure of the paper. An effective outline will make process of writing the research paper more efficient, allowing for ease of transitions between sections of the paper. When writing the paper, it is important to think through the structure of the paper and how to make a strong argument. Support for the argument should be based on concrete evidence, such as literary criticism, literary theory, and close readings of the poem. It is essential to have a clear argument that is consistent throughout the body of the paper.

Citing Sources

When writing a research paper it is also important to cite all sources that are used. The style used for citing sources will depend on the style guide indicated by the professor or the school’s guidelines. Whether using MLA, APA, or Chicago style, it is important to adhere to the style guide indicated in order to have a complete and well-written paper.

Once the research and outlining is complete, the process of drafting a poetry research paper can begin. When constructing the first draft, it is especially useful to re-read the poem and to recall evidence that supports the argument made about the poem. Additionally, it is important to proofread and edit the first draft in order to make the argument more clear and to check for any grammar or spelling errors.

Writing a research paper on poetry does not have to be a difficult task. By taking the time to properly research, analyze, and structure the paper, the process of writing a successful poetry research paper becomes easier. Following these steps— researching the poet, understanding the poem itself, outlining the paper, citing sources, and drafting the paper— will ensure a great and thorough paper is prepared.

Using Imagery and Metaphor

The use of imagery and metaphor is an essential element when writing poetry. Imagery can be used to provide vivid descriptions of scenes and characters, while metaphor can be used to create deeper meanings and analogies. Understanding the use of imagery and metaphor can help to break down the poem and discover hidden meanings. Students researching poetry should pay special attentions to the poetic devices used to further the story or allusions to other works, such as classical mythology. Paying close attention to the language, metaphors, and imagery used by the poet can help to uncover the true meaning of the poem. By breaking down the element of the poem and focusing on individual elements, it is much easier to make valid conclusions about the poem and its author.

Understanding Rhyme and Meter

Rhyme and meter are two of the most important and complex elements of poetry. These two poetic techniques are used to help the poet structure their poem to provide rhythm and flow. Most commonly, rhyme and meter help to provide emphasis to certain words or phrases to give them additional meaning. When analyzing poetry, it is important to pay attention to the written rhyme schemes and meter of the poem. There are various patterns of rhyme, such as couplets, tercets, and quatrains. Meter, usually governed by iambs and trochees, can give the poem an added sense of rhythm to further emphasize certain words, phrases, or thoughts.

Exploring Themes

Themes are the central ideas behind a poem. The themes of a poem can be subtle and can be found in the language and images used. Exploring the poem through a thematic analysis can help to identify the true meaning of the poem and the message that the poet is conveying. When researching a poem, it is important to identify the primary theme of the poem and to look for evidence in the poem that can be used to support the claim. By paying attention to the language of a poem, students can uncover the deeper meanings within the poem and can move past the literal interpretation of the poem.

Analyzing Discourse and Context

In addition to the written aspects of a poem, it is important to consider the historical and social context of the poem. The context of the poem can be used to further understand its deeper meanings and implications. Collingwood’s theory of re-enactment can be used to reconstruct the context of a poem in order to gain a deeper understanding of the poem. When researching a poem, it is important to consider the the time period in which the poem was written, the author’s other works, and the broader literary context of the poem. Examining the discourse used by the poet can help to uncover the true message of the poem and the impact on society at the time.

Finding Inspiration

When researching poetry, it is important for the student to find inspiration in the form of other authors, critics, and theorists. Studying the works of other authors can provide valuable insight into a poem and can inform the student’s own interpretations. In addition to studying critics and theorists, the student should also look to other poets and authors as sources of inspiration. The student can explore the works of similar poets or authors to learn how they use their poetic elements in their work. This can help students to gain insight into the language, imagery, and themes present in the poem being researched.

Minnie Walters

Minnie Walters is a passionate writer and lover of poetry. She has a deep knowledge and appreciation for the work of famous poets such as William Wordsworth, Emily Dickinson, Robert Frost, and many more. She hopes you will also fall in love with poetry!

Leave a Comment Cancel reply

• school Campus Bookshelves
• menu_book Bookshelves
• perm_media Learning Objects
• login Login
• how_to_reg Request Instructor Account
• hub Instructor Commons
• Download Page (PDF)
• Download Full Book (PDF)
• Periodic Table
• Physics Constants
• Scientific Calculator
• Reference & Cite
• Tools expand_more
• Readability

selected template will load here

This action is not available.

12.14: Sample Student Literary Analysis Essays

• Last updated
• Save as PDF
• Page ID 40514

• Heather Ringo & Athena Kashyap
• City College of San Francisco via ASCCC Open Educational Resources Initiative

The following examples are essays where student writers focused on close-reading a literary work.

While reading these examples, ask yourself the following questions:

• What is the essay's thesis statement, and how do you know it is the thesis statement?
• What is the main idea or topic sentence of each body paragraph, and how does it relate back to the thesis statement?
• Where and how does each essay use evidence (quotes or paraphrase from the literature)?
• What are some of the literary devices or structures the essays analyze or discuss?
• How does each author structure their conclusion, and how does their conclusion differ from their introduction?

Example 1: Poetry

Victoria Morillo

Instructor Heather Ringo

3 August 2022

How Nguyen’s Structure Solidifies the Impact of Sexual Violence in “The Study”

Stripped of innocence, your body taken from you. No matter how much you try to block out the instance in which these two things occurred, memories surface and come back to haunt you. How does a person, a young boy , cope with an event that forever changes his life? Hieu Minh Nguyen deconstructs this very way in which an act of sexual violence affects a survivor. In his poem, “The Study,” the poem's speaker recounts the year in which his molestation took place, describing how his memory filters in and out. Throughout the poem, Nguyen writes in free verse, permitting a structural liberation to become the foundation for his message to shine through. While he moves the readers with this poignant narrative, Nguyen effectively conveys the resulting internal struggles of feeling alone and unseen.

The speaker recalls his experience with such painful memory through the use of specific punctuation choices. Just by looking at the poem, we see that the first period doesn’t appear until line 14. It finally comes after the speaker reveals to his readers the possible, central purpose for writing this poem: the speaker's molestation. In the first half, the poem makes use of commas, em dashes, and colons, which lends itself to the idea of the speaker stringing along all of these details to make sense of this time in his life. If reading the poem following the conventions of punctuation, a sense of urgency is present here, as well. This is exemplified by the lack of periods to finalize a thought; and instead, Nguyen uses other punctuation marks to connect them. Serving as another connector of thoughts, the two em dashes give emphasis to the role memory plays when the speaker discusses how “no one [had] a face” during that time (Nguyen 9-11). He speaks in this urgent manner until the 14th line, and when he finally gets it off his chest, the pace of the poem changes, as does the more frequent use of the period. This stream-of-consciousness-like section when juxtaposed with the latter half of the poem, causes readers to slow down and pay attention to the details. It also splits the poem in two: a section that talks of the fogginess of memory then transitions into one that remembers it all.

In tandem with the fluctuating nature of memory, the utilization of line breaks and word choice help reflect the damage the molestation has had. Within the first couple of lines of the poem, the poem demands the readers’ attention when the line breaks from “floating” to “dead” as the speaker describes his memory of Little Billy (Nguyen 1-4). This line break averts the readers’ expectation of the direction of the narrative and immediately shifts the tone of the poem. The break also speaks to the effect his trauma has ingrained in him and how “[f]or the longest time,” his only memory of that year revolves around an image of a boy’s death. In a way, the speaker sees himself in Little Billy; or perhaps, he’s representative of the tragic death of his boyhood, how the speaker felt so “dead” after enduring such a traumatic experience, even referring to himself as a “ghost” that he tries to evict from his conscience (Nguyen 24). The feeling that a part of him has died is solidified at the very end of the poem when the speaker describes himself as a nine-year-old boy who’s been “fossilized,” forever changed by this act (Nguyen 29). By choosing words associated with permanence and death, the speaker tries to recreate the atmosphere (for which he felt trapped in) in order for readers to understand the loneliness that came as a result of his trauma. With the assistance of line breaks, more attention is drawn to the speaker's words, intensifying their importance, and demanding to be felt by the readers.

Most importantly, the speaker expresses eloquently, and so heartbreakingly, about the effect sexual violence has on a person. Perhaps what seems to be the most frustrating are the people who fail to believe survivors of these types of crimes. This is evident when he describes “how angry” the tenants were when they filled the pool with cement (Nguyen 4). They seem to represent how people in the speaker's life were dismissive of his assault and who viewed his tragedy as a nuisance of some sorts. This sentiment is bookended when he says, “They say, give us details , so I give them my body. / They say, give us proof , so I give them my body,” (Nguyen 25-26). The repetition of these two lines reinforces the feeling many feel in these scenarios, as they’re often left to deal with trying to make people believe them, or to even see them.

It’s important to recognize how the structure of this poem gives the speaker space to express the pain he’s had to carry for so long. As a characteristic of free verse, the poem doesn’t follow any structured rhyme scheme or meter; which in turn, allows him to not have any constraints in telling his story the way he wants to. The speaker has the freedom to display his experience in a way that evades predictability and engenders authenticity of a story very personal to him. As readers, we abandon anticipating the next rhyme, and instead focus our attention to the other ways, like his punctuation or word choice, in which he effectively tells his story. The speaker recognizes that some part of him no longer belongs to himself, but by writing “The Study,” he shows other survivors that they’re not alone and encourages hope that eventually, they will be freed from the shackles of sexual violence.

Works Cited

Nguyen, Hieu Minh. “The Study” Poets.Org. Academy of American Poets, Coffee House Press, 2018, https://poets.org/poem/study-0 .

Example 2: Fiction

Todd Goodwin

Professor Stan Matyshak

Advanced Expository Writing

Sept. 17, 20—

Poe’s “Usher”: A Mirror of the Fall of the House of Humanity

Right from the outset of the grim story, “The Fall of the House of Usher,” Edgar Allan Poe enmeshes us in a dark, gloomy, hopeless world, alienating his characters and the reader from any sort of physical or psychological norm where such values as hope and happiness could possibly exist. He fatalistically tells the story of how a man (the narrator) comes from the outside world of hope, religion, and everyday society and tries to bring some kind of redeeming happiness to his boyhood friend, Roderick Usher, who not only has physically and psychologically wasted away but is entrapped in a dilapidated house of ever-looming terror with an emaciated and deranged twin sister. Roderick Usher embodies the wasting away of what once was vibrant and alive, and his house of “insufferable gloom” (273), which contains his morbid sister, seems to mirror or reflect this fear of death and annihilation that he most horribly endures. A close reading of the story reveals that Poe uses mirror images, or reflections, to contribute to the fatalistic theme of “Usher”: each reflection serves to intensify an already prevalent tone of hopelessness, darkness, and fatalism.

It could be argued that the house of Roderick Usher is a “house of mirrors,” whose unpleasant and grim reflections create a dark and hopeless setting. For example, the narrator first approaches “the melancholy house of Usher on a dark and soundless day,” and finds a building which causes him a “sense of insufferable gloom,” which “pervades his spirit and causes an iciness, a sinking, a sickening of the heart, an undiscerned dreariness of thought” (273). The narrator then optimistically states: “I reflected that a mere different arrangement of the scene, of the details of the picture, would be sufficient to modify, or perhaps annihilate its capacity for sorrowful impression” (274). But the narrator then sees the reflection of the house in the tarn and experiences a “shudder even more thrilling than before” (274). Thus the reader begins to realize that the narrator cannot change or stop the impending doom that will befall the house of Usher, and maybe humanity. The story cleverly plays with the word reflection : the narrator sees a physical reflection that leads him to a mental reflection about Usher’s surroundings.

The narrator’s disillusionment by such grim reflection continues in the story. For example, he describes Roderick Usher’s face as distinct with signs of old strength but lost vigor: the remains of what used to be. He describes the house as a once happy and vibrant place, which, like Roderick, lost its vitality. Also, the narrator describes Usher’s hair as growing wild on his rather obtrusive head, which directly mirrors the eerie moss and straw covering the outside of the house. The narrator continually longs to see these bleak reflections as a dream, for he states: “Shaking off from my spirit what must have been a dream, I scanned more narrowly the real aspect of the building” (276). He does not want to face the reality that Usher and his home are doomed to fall, regardless of what he does.

Although there are almost countless examples of these mirror images, two others stand out as important. First, Roderick and his sister, Madeline, are twins. The narrator aptly states just as he and Roderick are entombing Madeline that there is “a striking similitude between brother and sister” (288). Indeed, they are mirror images of each other. Madeline is fading away psychologically and physically, and Roderick is not too far behind! The reflection of “doom” that these two share helps intensify and symbolize the hopelessness of the entire situation; thus, they further develop the fatalistic theme. Second, in the climactic scene where Madeline has been mistakenly entombed alive, there is a pairing of images and sounds as the narrator tries to calm Roderick by reading him a romance story. Events in the story simultaneously unfold with events of the sister escaping her tomb. In the story, the hero breaks out of the coffin. Then, in the story, the dragon’s shriek as he is slain parallels Madeline’s shriek. Finally, the story tells of the clangor of a shield, matched by the sister’s clanging along a metal passageway. As the suspense reaches its climax, Roderick shrieks his last words to his “friend,” the narrator: “Madman! I tell you that she now stands without the door” (296).

Roderick, who slowly falls into insanity, ironically calls the narrator the “Madman.” We are left to reflect on what Poe means by this ironic twist. Poe’s bleak and dark imagery, and his use of mirror reflections, seem only to intensify the hopelessness of “Usher.” We can plausibly conclude that, indeed, the narrator is the “Madman,” for he comes from everyday society, which is a place where hope and faith exist. Poe would probably argue that such a place is opposite to the world of Usher because a world where death is inevitable could not possibly hold such positive values. Therefore, just as Roderick mirrors his sister, the reflection in the tarn mirrors the dilapidation of the house, and the story mirrors the final actions before the death of Usher. “The Fall of the House of Usher” reflects Poe’s view that humanity is hopelessly doomed.

Poe, Edgar Allan. “The Fall of the House of Usher.” 1839. Electronic Text Center, University of Virginia Library . 1995. Web. 1 July 2012. < http://etext.virginia.edu/toc/modeng/public/PoeFall.html >.

Example 3: Poetry

Amy Chisnell

Professor Laura Neary

Writing and Literature

April 17, 20—

Don’t Listen to the Egg!: A Close Reading of Lewis Carroll’s “Jabberwocky”

“You seem very clever at explaining words, Sir,” said Alice. “Would you kindly tell me the meaning of the poem called ‘Jabberwocky’?”

“Let’s hear it,” said Humpty Dumpty. “I can explain all the poems that ever were invented—and a good many that haven’t been invented just yet.” (Carroll 164)

In Lewis Carroll’s Through the Looking-Glass , Humpty Dumpty confidently translates (to a not so confident Alice) the complicated language of the poem “Jabberwocky.” The words of the poem, though nonsense, aptly tell the story of the slaying of the Jabberwock. Upon finding “Jabberwocky” on a table in the looking-glass room, Alice is confused by the strange words. She is quite certain that “ somebody killed something ,” but she does not understand much more than that. When later she encounters Humpty Dumpty, she seizes the opportunity at having the knowledgeable egg interpret—or translate—the poem. Since Humpty Dumpty professes to be able to “make a word work” for him, he is quick to agree. Thus he acts like a New Critic who interprets the poem by performing a close reading of it. Through Humpty’s interpretation of the first stanza, however, we see the poem’s deeper comment concerning the practice of interpreting poetry and literature in general—that strict analytical translation destroys the beauty of a poem. In fact, Humpty Dumpty commits the “heresy of paraphrase,” for he fails to understand that meaning cannot be separated from the form or structure of the literary work.

Of the 71 words found in “Jabberwocky,” 43 have no known meaning. They are simply nonsense. Yet through this nonsensical language, the poem manages not only to tell a story but also gives the reader a sense of setting and characterization. One feels, rather than concretely knows, that the setting is dark, wooded, and frightening. The characters, such as the Jubjub bird, the Bandersnatch, and the doomed Jabberwock, also appear in the reader’s head, even though they will not be found in the local zoo. Even though most of the words are not real, the reader is able to understand what goes on because he or she is given free license to imagine what the words denote and connote. Simply, the poem’s nonsense words are the meaning.

Therefore, when Humpty interprets “Jabberwocky” for Alice, he is not doing her any favors, for he actually misreads the poem. Although the poem in its original is constructed from nonsense words, by the time Humpty is done interpreting it, it truly does not make any sense. The first stanza of the original poem is as follows:

’Twas brillig, and the slithy toves

Did gyre and gimble in the wabe;

All mimsy were the borogroves,

An the mome raths outgrabe. (Carroll 164)

If we replace, however, the nonsense words of “Jabberwocky” with Humpty’s translated words, the effect would be something like this:

’Twas four o’clock in the afternoon, and the lithe and slimy badger-lizard-corkscrew creatures

Did go round and round and make holes in the grass-plot round the sun-dial:

All flimsy and miserable were the shabby-looking birds

with mop feathers,

And the lost green pigs bellowed-sneezed-whistled.

By translating the poem in such a way, Humpty removes the charm or essence—and the beauty, grace, and rhythm—from the poem. The poetry is sacrificed for meaning. Humpty Dumpty commits the heresy of paraphrase. As Cleanth Brooks argues, “The structure of a poem resembles that of a ballet or musical composition. It is a pattern of resolutions and balances and harmonizations” (203). When the poem is left as nonsense, the reader can easily imagine what a “slithy tove” might be, but when Humpty tells us what it is, he takes that imaginative license away from the reader. The beauty (if that is the proper word) of “Jabberwocky” is in not knowing what the words mean, and yet understanding. By translating the poem, Humpty takes that privilege from the reader. In addition, Humpty fails to recognize that meaning cannot be separated from the structure itself: the nonsense poem reflects this literally—it means “nothing” and achieves this meaning by using “nonsense” words.

Furthermore, the nonsense words Carroll chooses to use in “Jabberwocky” have a magical effect upon the reader; the shadowy sound of the words create the atmosphere, which may be described as a trance-like mood. When Alice first reads the poem, she says it seems to fill her head “with ideas.” The strange-sounding words in the original poem do give one ideas. Why is this? Even though the reader has never heard these words before, he or she is instantly aware of the murky, mysterious mood they set. In other words, diction operates not on the denotative level (the dictionary meaning) but on the connotative level (the emotion(s) they evoke). Thus “Jabberwocky” creates a shadowy mood, and the nonsense words are instrumental in creating this mood. Carroll could not have simply used any nonsense words.

For example, let us change the “dark,” “ominous” words of the first stanza to “lighter,” more “comic” words:

’Twas mearly, and the churly pells

Did bimble and ringle in the tink;

All timpy were the brimbledimps,

And the bip plips outlink.

Shifting the sounds of the words from dark to light merely takes a shift in thought. To create a specific mood using nonsense words, one must create new words from old words that convey the desired mood. In “Jabberwocky,” Carroll mixes “slimy,” a grim idea, “lithe,” a pliable image, to get a new adjective: “slithy” (a portmanteau word). In this translation, brighter words were used to get a lighter effect. “Mearly” is a combination of “morning” and “early,” and “ringle” is a blend of “ring” and "dingle.” The point is that “Jabberwocky’s” nonsense words are created specifically to convey this shadowy or mysterious mood and are integral to the “meaning.”

Consequently, Humpty’s rendering of the poem leaves the reader with a completely different feeling than does the original poem, which provided us with a sense of ethereal mystery, of a dark and foreign land with exotic creatures and fantastic settings. The mysteriousness is destroyed by Humpty’s literal paraphrase of the creatures and the setting; by doing so, he has taken the beauty away from the poem in his attempt to understand it. He has committed the heresy of paraphrase: “If we allow ourselves to be misled by it [this heresy], we distort the relation of the poem to its ‘truth’… we split the poem between its ‘form’ and its ‘content’” (Brooks 201). Humpty Dumpty’s ultimate demise might be seen to symbolize the heretical split between form and content: as a literary creation, Humpty Dumpty is an egg, a well-wrought urn of nonsense. His fall from the wall cracks him and separates the contents from the container, and not even all the King’s men can put the scrambled egg back together again!

Through the odd characters of a little girl and a foolish egg, “Jabberwocky” suggests a bit of sage advice about reading poetry, advice that the New Critics built their theories on. The importance lies not solely within strict analytical translation or interpretation, but in the overall effect of the imagery and word choice that evokes a meaning inseparable from those literary devices. As Archibald MacLeish so aptly writes: “A poem should not mean / But be.” Sometimes it takes a little nonsense to show us the sense in something.

Brooks, Cleanth. The Well-Wrought Urn: Studies in the Structure of Poetry . 1942. San Diego: Harcourt Brace, 1956. Print.

Carroll, Lewis. Through the Looking-Glass. Alice in Wonderland . 2nd ed. Ed. Donald J. Gray. New York: Norton, 1992. Print.

MacLeish, Archibald. “Ars Poetica.” The Oxford Book of American Poetry . Ed. David Lehman. Oxford: Oxford UP, 2006. 385–86. Print.

Attribution

• Sample Essay 1 received permission from Victoria Morillo to publish, licensed Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International ( CC BY-NC-SA 4.0 )
• Sample Essays 2 and 3 adapted from Cordell, Ryan and John Pennington. "2.5: Student Sample Papers" from Creating Literary Analysis. 2012. Licensed Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported ( CC BY-NC-SA 3.0 )

How to Write a Poem Analysis in 4 Steps

This post may contains affiliate links. If you click and buy we may make a commission, at no additional charge to you. Please see our disclosure policy for more details.

Poetry is a form of writing that touches a reader’s soul and evokes many emotions. The poet beautifully expresses a story or thought in a few lines that convey deep meanings.

People who love to read poetry prefer to research and write an in-depth analysis of the written piece to understand the whole idea behind the poem.

However, there is a process to write an analysis of a poem.

If you are wondering how to write a poem analysis, then you are in the right place. This article will discuss the necessary things to consider while analyzing a poem and list the 4 essential steps to follow to write a poetry analysis.

Check out the post to learn more.

Table of Contents

What is Poetry Analysis?

In literature, poetry is a type of writing that uses style, sound, and rhythm to stir a reader’s emotions, ideas, and imagination.

Poetry analysis is the process of decoding a poem to understand the overall message it is trying to convey. It includes examining the elements, word usage, content, format, tone, etc.

Analyzing a poem helps to comprehend the written piece, its context, themes, and ideas. Interpreting the poem leads to a deeper understanding and appreciation of the written work.

This type of writing explores ideas universally and covers many emotions so the readers become aware of their own sentiments and feel a more profound connection

How to Analyze a Poem?

Before you begin writing a poetry analysis, you need to know how to analyze a poem. You must thoroughly decipher the entire poem for an in-depth understanding of the subject and its background details.

The very first step is to read the poem aloud. Read it slowly and carefully.

I have listed some of the mandatory things to take into consideration for writing a well-articulated poem analysis essay.

Title of the Poem

Most poems have a dedicated title, and you must start from here. A poet chooses a title that aligns with the inner meaning of the poem, and decoding the connection will help to understand the overall message.

The title might tell the basic idea of the poem, so always look for a relation between the title and the content of the written work. You can find the hidden inner meanings.

Although a few poets play with the name of the poem, so ensure to catch the intention.

Background of the Poem

A thorough analysis of a poem needs a background study. The written work must have some story behind its creation, and determining it can help to understand the poem in detail.

Background study includes the period when the poem was written, the topic it is discussing, the author’s story or situation at that time, the motivation behind it, etc.

Maybe the poet was suffering and wrote a poem related to his experience, or he particularly wrote about world issues, war, or love.

This research will give you an idea about the poet’s intent and the poem’s overall meaning.

Structure of the Poem

The structure of the poem is also essential. The components of a structure are verse, rhyme, meter, and line break. Each poem has these elements in a different style.

The author decides the poem’s structure. A poem analysis includes an explanation of the structure, so it is necessary to understand the types before analyzing.

The tone of poems differs according to the mood or intention of the poets. Its analysis depends on the speaker and the recipient..

Language and Symbols

Poets use figurative language, symbols, and other techniques to make a poem more imaginative and descriptive.

Using metaphor, simile, personification, etc., is a way to make the poem realistic and give it an in-depth meaning so that readers can relate to it personally.

Various language forms and symbols convey intricate thoughts and experiences. The reader must know about these forms and techniques to understand the meaning in detail.

In poetic terms, music means the rhyme and rhythm of the written piece. All components of a poem, such as rhyme, line breaks, meter, rhythm, sound elements, words, etc., contribute together to give the poem a music of its own.

Observe these elements while analyzing to get a vision of the written work.

Purpose of the Poem

You cannot leave the motive behind writing a poem. Every piece is written for a particular purpose; as a reader, you must learn to find it.

The purpose of a poem can be to discuss societal issues, share life experiences, express deep emotions, and more. Reading and understanding the purpose will help to enhance the analysis.

How to Write a Poem Analysis in 4 Simple Steps

After analyzing the poem, you can now easily write a poem analysis. Following a structure will help to write a well-organized and detailed essay. Check out the 4 steps provided below for writing a poem analysis.

• Step 1 : Read the poem
• Step 2 : Analyze the poem thoroughly and note the necessary details
• Title and Author
• A thesis statement. Key elements to be analyzed
• Background and theme
• Detailed meaning of the poem
• Structure and Tone 
• Language forms
• Symbols 
• Sound Effects
• Step 4 : Rectify any errors

Following these steps, you can write a good poetry analysis; however, adding your personal opinion about the poem is essential.

I hope this article on how to write a poem analysis will help you to create a well-detailed analysis of your favorite poem. 

Poems are a beautiful way to express emotions, and as readers, we enjoy reading beautiful poetry from famous poets. 

What is your favorite poem?

Leave a Comment Cancel reply

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• My Account Login
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 26 March 2024

Predicting and improving complex beer flavor through machine learning

• Michiel Schreurs   ORCID: orcid.org/0000-0002-9449-5619 1 , 2 , 3   na1 ,
• Supinya Piampongsant 1 , 2 , 3   na1 ,
• Miguel Roncoroni   ORCID: orcid.org/0000-0001-7461-1427 1 , 2 , 3   na1 ,
• Lloyd Cool   ORCID: orcid.org/0000-0001-9936-3124 1 , 2 , 3 , 4 ,
• Beatriz Herrera-Malaver   ORCID: orcid.org/0000-0002-5096-9974 1 , 2 , 3 ,
• Christophe Vanderaa   ORCID: orcid.org/0000-0001-7443-5427 4 ,
• Florian A. Theßeling 1 , 2 , 3 ,
• Łukasz Kreft   ORCID: orcid.org/0000-0001-7620-4657 5 ,
• Alexander Botzki   ORCID: orcid.org/0000-0001-6691-4233 5 ,
• Philippe Malcorps 6 ,
• Luk Daenen 6 ,
• Tom Wenseleers   ORCID: orcid.org/0000-0002-1434-861X 4 &
• Kevin J. Verstrepen   ORCID: orcid.org/0000-0002-3077-6219 1 , 2 , 3  

Nature Communications volume  15 , Article number:  2368 ( 2024 ) Cite this article

52k Accesses

856 Altmetric

Metrics details

• Chemical engineering
• Gas chromatography
• Machine learning
• Metabolomics
• Taste receptors

The perception and appreciation of food flavor depends on many interacting chemical compounds and external factors, and therefore proves challenging to understand and predict. Here, we combine extensive chemical and sensory analyses of 250 different beers to train machine learning models that allow predicting flavor and consumer appreciation. For each beer, we measure over 200 chemical properties, perform quantitative descriptive sensory analysis with a trained tasting panel and map data from over 180,000 consumer reviews to train 10 different machine learning models. The best-performing algorithm, Gradient Boosting, yields models that significantly outperform predictions based on conventional statistics and accurately predict complex food features and consumer appreciation from chemical profiles. Model dissection allows identifying specific and unexpected compounds as drivers of beer flavor and appreciation. Adding these compounds results in variants of commercial alcoholic and non-alcoholic beers with improved consumer appreciation. Together, our study reveals how big data and machine learning uncover complex links between food chemistry, flavor and consumer perception, and lays the foundation to develop novel, tailored foods with superior flavors.

Similar content being viewed by others

BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules

Rudraksh Tuwani, Somin Wadhwa & Ganesh Bagler

Sensory lexicon and aroma volatiles analysis of brewing malt

Xiaoxia Su, Miao Yu, … Tianyi Du

Predicting odor from molecular structure: a multi-label classification approach

Kushagra Saini & Venkatnarayan Ramanathan

Introduction

Predicting and understanding food perception and appreciation is one of the major challenges in food science. Accurate modeling of food flavor and appreciation could yield important opportunities for both producers and consumers, including quality control, product fingerprinting, counterfeit detection, spoilage detection, and the development of new products and product combinations (food pairing) 1 , 2 , 3 , 4 , 5 , 6 . Accurate models for flavor and consumer appreciation would contribute greatly to our scientific understanding of how humans perceive and appreciate flavor. Moreover, accurate predictive models would also facilitate and standardize existing food assessment methods and could supplement or replace assessments by trained and consumer tasting panels, which are variable, expensive and time-consuming 7 , 8 , 9 . Lastly, apart from providing objective, quantitative, accurate and contextual information that can help producers, models can also guide consumers in understanding their personal preferences 10 .

Despite the myriad of applications, predicting food flavor and appreciation from its chemical properties remains a largely elusive goal in sensory science, especially for complex food and beverages 11 , 12 . A key obstacle is the immense number of flavor-active chemicals underlying food flavor. Flavor compounds can vary widely in chemical structure and concentration, making them technically challenging and labor-intensive to quantify, even in the face of innovations in metabolomics, such as non-targeted metabolic fingerprinting 13 , 14 . Moreover, sensory analysis is perhaps even more complicated. Flavor perception is highly complex, resulting from hundreds of different molecules interacting at the physiochemical and sensorial level. Sensory perception is often non-linear, characterized by complex and concentration-dependent synergistic and antagonistic effects 15 , 16 , 17 , 18 , 19 , 20 , 21 that are further convoluted by the genetics, environment, culture and psychology of consumers 22 , 23 , 24 . Perceived flavor is therefore difficult to measure, with problems of sensitivity, accuracy, and reproducibility that can only be resolved by gathering sufficiently large datasets 25 . Trained tasting panels are considered the prime source of quality sensory data, but require meticulous training, are low throughput and high cost. Public databases containing consumer reviews of food products could provide a valuable alternative, especially for studying appreciation scores, which do not require formal training 25 . Public databases offer the advantage of amassing large amounts of data, increasing the statistical power to identify potential drivers of appreciation. However, public datasets suffer from biases, including a bias in the volunteers that contribute to the database, as well as confounding factors such as price, cult status and psychological conformity towards previous ratings of the product.

Classical multivariate statistics and machine learning methods have been used to predict flavor of specific compounds by, for example, linking structural properties of a compound to its potential biological activities or linking concentrations of specific compounds to sensory profiles 1 , 26 . Importantly, most previous studies focused on predicting organoleptic properties of single compounds (often based on their chemical structure) 27 , 28 , 29 , 30 , 31 , 32 , 33 , thus ignoring the fact that these compounds are present in a complex matrix in food or beverages and excluding complex interactions between compounds. Moreover, the classical statistics commonly used in sensory science 34 , 35 , 36 , 37 , 38 , 39 require a large sample size and sufficient variance amongst predictors to create accurate models. They are not fit for studying an extensive set of hundreds of interacting flavor compounds, since they are sensitive to outliers, have a high tendency to overfit and are less suited for non-linear and discontinuous relationships 40 .

In this study, we combine extensive chemical analyses and sensory data of a set of different commercial beers with machine learning approaches to develop models that predict taste, smell, mouthfeel and appreciation from compound concentrations. Beer is particularly suited to model the relationship between chemistry, flavor and appreciation. First, beer is a complex product, consisting of thousands of flavor compounds that partake in complex sensory interactions 41 , 42 , 43 . This chemical diversity arises from the raw materials (malt, yeast, hops, water and spices) and biochemical conversions during the brewing process (kilning, mashing, boiling, fermentation, maturation and aging) 44 , 45 . Second, the advent of the internet saw beer consumers embrace online review platforms, such as RateBeer (ZX Ventures, Anheuser-Busch InBev SA/NV) and BeerAdvocate (Next Glass, inc.). In this way, the beer community provides massive data sets of beer flavor and appreciation scores, creating extraordinarily large sensory databases to complement the analyses of our professional sensory panel. Specifically, we characterize over 200 chemical properties of 250 commercial beers, spread across 22 beer styles, and link these to the descriptive sensory profiling data of a 16-person in-house trained tasting panel and data acquired from over 180,000 public consumer reviews. These unique and extensive datasets enable us to train a suite of machine learning models to predict flavor and appreciation from a beer’s chemical profile. Dissection of the best-performing models allows us to pinpoint specific compounds as potential drivers of beer flavor and appreciation. Follow-up experiments confirm the importance of these compounds and ultimately allow us to significantly improve the flavor and appreciation of selected commercial beers. Together, our study represents a significant step towards understanding complex flavors and reinforces the value of machine learning to develop and refine complex foods. In this way, it represents a stepping stone for further computer-aided food engineering applications 46 .

To generate a comprehensive dataset on beer flavor, we selected 250 commercial Belgian beers across 22 different beer styles (Supplementary Fig.  S1 ). Beers with ≤ 4.2% alcohol by volume (ABV) were classified as non-alcoholic and low-alcoholic. Blonds and Tripels constitute a significant portion of the dataset (12.4% and 11.2%, respectively) reflecting their presence on the Belgian beer market and the heterogeneity of beers within these styles. By contrast, lager beers are less diverse and dominated by a handful of brands. Rare styles such as Brut or Faro make up only a small fraction of the dataset (2% and 1%, respectively) because fewer of these beers are produced and because they are dominated by distinct characteristics in terms of flavor and chemical composition.

Extensive analysis identifies relationships between chemical compounds in beer

For each beer, we measured 226 different chemical properties, including common brewing parameters such as alcohol content, iso-alpha acids, pH, sugar concentration 47 , and over 200 flavor compounds (Methods, Supplementary Table  S1 ). A large portion (37.2%) are terpenoids arising from hopping, responsible for herbal and fruity flavors 16 , 48 . A second major category are yeast metabolites, such as esters and alcohols, that result in fruity and solvent notes 48 , 49 , 50 . Other measured compounds are primarily derived from malt, or other microbes such as non- Saccharomyces yeasts and bacteria (‘wild flora’). Compounds that arise from spices or staling are labeled under ‘Others’. Five attributes (caloric value, total acids and total ester, hop aroma and sulfur compounds) are calculated from multiple individually measured compounds.

As a first step in identifying relationships between chemical properties, we determined correlations between the concentrations of the compounds (Fig.  1 , upper panel, Supplementary Data  1 and 2 , and Supplementary Fig.  S2 . For the sake of clarity, only a subset of the measured compounds is shown in Fig.  1 ). Compounds of the same origin typically show a positive correlation, while absence of correlation hints at parameters varying independently. For example, the hop aroma compounds citronellol, and alpha-terpineol show moderate correlations with each other (Spearman’s rho=0.39 and 0.57), but not with the bittering hop component iso-alpha acids (Spearman’s rho=0.16 and −0.07). This illustrates how brewers can independently modify hop aroma and bitterness by selecting hop varieties and dosage time. If hops are added early in the boiling phase, chemical conversions increase bitterness while aromas evaporate, conversely, late addition of hops preserves aroma but limits bitterness 51 . Similarly, hop-derived iso-alpha acids show a strong anti-correlation with lactic acid and acetic acid, likely reflecting growth inhibition of lactic acid and acetic acid bacteria, or the consequent use of fewer hops in sour beer styles, such as West Flanders ales and Fruit beers, that rely on these bacteria for their distinct flavors 52 . Finally, yeast-derived esters (ethyl acetate, ethyl decanoate, ethyl hexanoate, ethyl octanoate) and alcohols (ethanol, isoamyl alcohol, isobutanol, and glycerol), correlate with Spearman coefficients above 0.5, suggesting that these secondary metabolites are correlated with the yeast genetic background and/or fermentation parameters and may be difficult to influence individually, although the choice of yeast strain may offer some control 53 .

Spearman rank correlations are shown. Descriptors are grouped according to their origin (malt (blue), hops (green), yeast (red), wild flora (yellow), Others (black)), and sensory aspect (aroma, taste, palate, and overall appreciation). Please note that for the chemical compounds, for the sake of clarity, only a subset of the total number of measured compounds is shown, with an emphasis on the key compounds for each source. For more details, see the main text and Methods section. Chemical data can be found in Supplementary Data  1 , correlations between all chemical compounds are depicted in Supplementary Fig.  S2 and correlation values can be found in Supplementary Data  2 . See Supplementary Data  4 for sensory panel assessments and Supplementary Data  5 for correlation values between all sensory descriptors.

Interestingly, different beer styles show distinct patterns for some flavor compounds (Supplementary Fig.  S3 ). These observations agree with expectations for key beer styles, and serve as a control for our measurements. For instance, Stouts generally show high values for color (darker), while hoppy beers contain elevated levels of iso-alpha acids, compounds associated with bitter hop taste. Acetic and lactic acid are not prevalent in most beers, with notable exceptions such as Kriek, Lambic, Faro, West Flanders ales and Flanders Old Brown, which use acid-producing bacteria ( Lactobacillus and Pediococcus ) or unconventional yeast ( Brettanomyces ) 54 , 55 . Glycerol, ethanol and esters show similar distributions across all beer styles, reflecting their common origin as products of yeast metabolism during fermentation 45 , 53 . Finally, low/no-alcohol beers contain low concentrations of glycerol and esters. This is in line with the production process for most of the low/no-alcohol beers in our dataset, which are produced through limiting fermentation or by stripping away alcohol via evaporation or dialysis, with both methods having the unintended side-effect of reducing the amount of flavor compounds in the final beer 56 , 57 .

Besides expected associations, our data also reveals less trivial associations between beer styles and specific parameters. For example, geraniol and citronellol, two monoterpenoids responsible for citrus, floral and rose flavors and characteristic of Citra hops, are found in relatively high amounts in Christmas, Saison, and Brett/co-fermented beers, where they may originate from terpenoid-rich spices such as coriander seeds instead of hops 58 .

Tasting panel assessments reveal sensorial relationships in beer

To assess the sensory profile of each beer, a trained tasting panel evaluated each of the 250 beers for 50 sensory attributes, including different hop, malt and yeast flavors, off-flavors and spices. Panelists used a tasting sheet (Supplementary Data  3 ) to score the different attributes. Panel consistency was evaluated by repeating 12 samples across different sessions and performing ANOVA. In 95% of cases no significant difference was found across sessions ( p  > 0.05), indicating good panel consistency (Supplementary Table  S2 ).

Aroma and taste perception reported by the trained panel are often linked (Fig.  1 , bottom left panel and Supplementary Data  4 and 5 ), with high correlations between hops aroma and taste (Spearman’s rho=0.83). Bitter taste was found to correlate with hop aroma and taste in general (Spearman’s rho=0.80 and 0.69), and particularly with “grassy” noble hops (Spearman’s rho=0.75). Barnyard flavor, most often associated with sour beers, is identified together with stale hops (Spearman’s rho=0.97) that are used in these beers. Lactic and acetic acid, which often co-occur, are correlated (Spearman’s rho=0.66). Interestingly, sweetness and bitterness are anti-correlated (Spearman’s rho = −0.48), confirming the hypothesis that they mask each other 59 , 60 . Beer body is highly correlated with alcohol (Spearman’s rho = 0.79), and overall appreciation is found to correlate with multiple aspects that describe beer mouthfeel (alcohol, carbonation; Spearman’s rho= 0.32, 0.39), as well as with hop and ester aroma intensity (Spearman’s rho=0.39 and 0.35).

Similar to the chemical analyses, sensorial analyses confirmed typical features of specific beer styles (Supplementary Fig.  S4 ). For example, sour beers (Faro, Flanders Old Brown, Fruit beer, Kriek, Lambic, West Flanders ale) were rated acidic, with flavors of both acetic and lactic acid. Hoppy beers were found to be bitter and showed hop-associated aromas like citrus and tropical fruit. Malt taste is most detected among scotch, stout/porters, and strong ales, while low/no-alcohol beers, which often have a reputation for being ‘worty’ (reminiscent of unfermented, sweet malt extract) appear in the middle. Unsurprisingly, hop aromas are most strongly detected among hoppy beers. Like its chemical counterpart (Supplementary Fig.  S3 ), acidity shows a right-skewed distribution, with the most acidic beers being Krieks, Lambics, and West Flanders ales.

Tasting panel assessments of specific flavors correlate with chemical composition

We find that the concentrations of several chemical compounds strongly correlate with specific aroma or taste, as evaluated by the tasting panel (Fig.  2 , Supplementary Fig.  S5 , Supplementary Data  6 ). In some cases, these correlations confirm expectations and serve as a useful control for data quality. For example, iso-alpha acids, the bittering compounds in hops, strongly correlate with bitterness (Spearman’s rho=0.68), while ethanol and glycerol correlate with tasters’ perceptions of alcohol and body, the mouthfeel sensation of fullness (Spearman’s rho=0.82/0.62 and 0.72/0.57 respectively) and darker color from roasted malts is a good indication of malt perception (Spearman’s rho=0.54).

Heatmap colors indicate Spearman’s Rho. Axes are organized according to sensory categories (aroma, taste, mouthfeel, overall), chemical categories and chemical sources in beer (malt (blue), hops (green), yeast (red), wild flora (yellow), Others (black)). See Supplementary Data  6 for all correlation values.

Interestingly, for some relationships between chemical compounds and perceived flavor, correlations are weaker than expected. For example, the rose-smelling phenethyl acetate only weakly correlates with floral aroma. This hints at more complex relationships and interactions between compounds and suggests a need for a more complex model than simple correlations. Lastly, we uncovered unexpected correlations. For instance, the esters ethyl decanoate and ethyl octanoate appear to correlate slightly with hop perception and bitterness, possibly due to their fruity flavor. Iron is anti-correlated with hop aromas and bitterness, most likely because it is also anti-correlated with iso-alpha acids. This could be a sign of metal chelation of hop acids 61 , given that our analyses measure unbound hop acids and total iron content, or could result from the higher iron content in dark and Fruit beers, which typically have less hoppy and bitter flavors 62 .

Public consumer reviews complement expert panel data

To complement and expand the sensory data of our trained tasting panel, we collected 180,000 reviews of our 250 beers from the online consumer review platform RateBeer. This provided numerical scores for beer appearance, aroma, taste, palate, overall quality as well as the average overall score.

Public datasets are known to suffer from biases, such as price, cult status and psychological conformity towards previous ratings of a product. For example, prices correlate with appreciation scores for these online consumer reviews (rho=0.49, Supplementary Fig.  S6 ), but not for our trained tasting panel (rho=0.19). This suggests that prices affect consumer appreciation, which has been reported in wine 63 , while blind tastings are unaffected. Moreover, we observe that some beer styles, like lagers and non-alcoholic beers, generally receive lower scores, reflecting that online reviewers are mostly beer aficionados with a preference for specialty beers over lager beers. In general, we find a modest correlation between our trained panel’s overall appreciation score and the online consumer appreciation scores (Fig.  3 , rho=0.29). Apart from the aforementioned biases in the online datasets, serving temperature, sample freshness and surroundings, which are all tightly controlled during the tasting panel sessions, can vary tremendously across online consumers and can further contribute to (among others, appreciation) differences between the two categories of tasters. Importantly, in contrast to the overall appreciation scores, for many sensory aspects the results from the professional panel correlated well with results obtained from RateBeer reviews. Correlations were highest for features that are relatively easy to recognize even for untrained tasters, like bitterness, sweetness, alcohol and malt aroma (Fig.  3 and below).

RateBeer text mining results can be found in Supplementary Data  7 . Rho values shown are Spearman correlation values, with asterisks indicating significant correlations ( p  < 0.05, two-sided). All p values were smaller than 0.001, except for Esters aroma (0.0553), Esters taste (0.3275), Esters aroma—banana (0.0019), Coriander (0.0508) and Diacetyl (0.0134).

Besides collecting consumer appreciation from these online reviews, we developed automated text analysis tools to gather additional data from review texts (Supplementary Data  7 ). Processing review texts on the RateBeer database yielded comparable results to the scores given by the trained panel for many common sensory aspects, including acidity, bitterness, sweetness, alcohol, malt, and hop tastes (Fig.  3 ). This is in line with what would be expected, since these attributes require less training for accurate assessment and are less influenced by environmental factors such as temperature, serving glass and odors in the environment. Consumer reviews also correlate well with our trained panel for 4-vinyl guaiacol, a compound associated with a very characteristic aroma. By contrast, correlations for more specific aromas like ester, coriander or diacetyl are underrepresented in the online reviews, underscoring the importance of using a trained tasting panel and standardized tasting sheets with explicit factors to be scored for evaluating specific aspects of a beer. Taken together, our results suggest that public reviews are trustworthy for some, but not all, flavor features and can complement or substitute taste panel data for these sensory aspects.

Models can predict beer sensory profiles from chemical data

The rich datasets of chemical analyses, tasting panel assessments and public reviews gathered in the first part of this study provided us with a unique opportunity to develop predictive models that link chemical data to sensorial features. Given the complexity of beer flavor, basic statistical tools such as correlations or linear regression may not always be the most suitable for making accurate predictions. Instead, we applied different machine learning models that can model both simple linear and complex interactive relationships. Specifically, we constructed a set of regression models to predict (a) trained panel scores for beer flavor and quality and (b) public reviews’ appreciation scores from beer chemical profiles. We trained and tested 10 different models (Methods), 3 linear regression-based models (simple linear regression with first-order interactions (LR), lasso regression with first-order interactions (Lasso), partial least squares regressor (PLSR)), 5 decision tree models (AdaBoost regressor (ABR), extra trees (ET), gradient boosting regressor (GBR), random forest (RF) and XGBoost regressor (XGBR)), 1 support vector regression (SVR), and 1 artificial neural network (ANN) model.

To compare the performance of our machine learning models, the dataset was randomly split into a training and test set, stratified by beer style. After a model was trained on data in the training set, its performance was evaluated on its ability to predict the test dataset obtained from multi-output models (based on the coefficient of determination, see Methods). Additionally, individual-attribute models were ranked per descriptor and the average rank was calculated, as proposed by Korneva et al. 64 . Importantly, both ways of evaluating the models’ performance agreed in general. Performance of the different models varied (Table  1 ). It should be noted that all models perform better at predicting RateBeer results than results from our trained tasting panel. One reason could be that sensory data is inherently variable, and this variability is averaged out with the large number of public reviews from RateBeer. Additionally, all tree-based models perform better at predicting taste than aroma. Linear models (LR) performed particularly poorly, with negative R 2 values, due to severe overfitting (training set R 2  = 1). Overfitting is a common issue in linear models with many parameters and limited samples, especially with interaction terms further amplifying the number of parameters. L1 regularization (Lasso) successfully overcomes this overfitting, out-competing multiple tree-based models on the RateBeer dataset. Similarly, the dimensionality reduction of PLSR avoids overfitting and improves performance, to some extent. Still, tree-based models (ABR, ET, GBR, RF and XGBR) show the best performance, out-competing the linear models (LR, Lasso, PLSR) commonly used in sensory science 65 .

GBR models showed the best overall performance in predicting sensory responses from chemical information, with R 2 values up to 0.75 depending on the predicted sensory feature (Supplementary Table  S4 ). The GBR models predict consumer appreciation (RateBeer) better than our trained panel’s appreciation (R 2 value of 0.67 compared to R 2 value of 0.09) (Supplementary Table  S3 and Supplementary Table  S4 ). ANN models showed intermediate performance, likely because neural networks typically perform best with larger datasets 66 . The SVR shows intermediate performance, mostly due to the weak predictions of specific attributes that lower the overall performance (Supplementary Table  S4 ).

Model dissection identifies specific, unexpected compounds as drivers of consumer appreciation

Next, we leveraged our models to infer important contributors to sensory perception and consumer appreciation. Consumer preference is a crucial sensory aspects, because a product that shows low consumer appreciation scores often does not succeed commercially 25 . Additionally, the requirement for a large number of representative evaluators makes consumer trials one of the more costly and time-consuming aspects of product development. Hence, a model for predicting chemical drivers of overall appreciation would be a welcome addition to the available toolbox for food development and optimization.

Since GBR models on our RateBeer dataset showed the best overall performance, we focused on these models. Specifically, we used two approaches to identify important contributors. First, rankings of the most important predictors for each sensorial trait in the GBR models were obtained based on impurity-based feature importance (mean decrease in impurity). High-ranked parameters were hypothesized to be either the true causal chemical properties underlying the trait, to correlate with the actual causal properties, or to take part in sensory interactions affecting the trait 67 (Fig.  4A ). In a second approach, we used SHAP 68 to determine which parameters contributed most to the model for making predictions of consumer appreciation (Fig.  4B ). SHAP calculates parameter contributions to model predictions on a per-sample basis, which can be aggregated into an importance score.

A The impurity-based feature importance (mean deviance in impurity, MDI) calculated from the Gradient Boosting Regression (GBR) model predicting RateBeer appreciation scores. The top 15 highest ranked chemical properties are shown. B SHAP summary plot for the top 15 parameters contributing to our GBR model. Each point on the graph represents a sample from our dataset. The color represents the concentration of that parameter, with bluer colors representing low values and redder colors representing higher values. Greater absolute values on the horizontal axis indicate a higher impact of the parameter on the prediction of the model. C Spearman correlations between the 15 most important chemical properties and consumer overall appreciation. Numbers indicate the Spearman Rho correlation coefficient, and the rank of this correlation compared to all other correlations. The top 15 important compounds were determined using SHAP (panel B).

Both approaches identified ethyl acetate as the most predictive parameter for beer appreciation (Fig.  4 ). Ethyl acetate is the most abundant ester in beer with a typical ‘fruity’, ‘solvent’ and ‘alcoholic’ flavor, but is often considered less important than other esters like isoamyl acetate. The second most important parameter identified by SHAP is ethanol, the most abundant beer compound after water. Apart from directly contributing to beer flavor and mouthfeel, ethanol drastically influences the physical properties of beer, dictating how easily volatile compounds escape the beer matrix to contribute to beer aroma 69 . Importantly, it should also be noted that the importance of ethanol for appreciation is likely inflated by the very low appreciation scores of non-alcoholic beers (Supplementary Fig.  S4 ). Despite not often being considered a driver of beer appreciation, protein level also ranks highly in both approaches, possibly due to its effect on mouthfeel and body 70 . Lactic acid, which contributes to the tart taste of sour beers, is the fourth most important parameter identified by SHAP, possibly due to the generally high appreciation of sour beers in our dataset.

Interestingly, some of the most important predictive parameters for our model are not well-established as beer flavors or are even commonly regarded as being negative for beer quality. For example, our models identify methanethiol and ethyl phenyl acetate, an ester commonly linked to beer staling 71 , as a key factor contributing to beer appreciation. Although there is no doubt that high concentrations of these compounds are considered unpleasant, the positive effects of modest concentrations are not yet known 72 , 73 .

To compare our approach to conventional statistics, we evaluated how well the 15 most important SHAP-derived parameters correlate with consumer appreciation (Fig.  4C ). Interestingly, only 6 of the properties derived by SHAP rank amongst the top 15 most correlated parameters. For some chemical compounds, the correlations are so low that they would have likely been considered unimportant. For example, lactic acid, the fourth most important parameter, shows a bimodal distribution for appreciation, with sour beers forming a separate cluster, that is missed entirely by the Spearman correlation. Additionally, the correlation plots reveal outliers, emphasizing the need for robust analysis tools. Together, this highlights the need for alternative models, like the Gradient Boosting model, that better grasp the complexity of (beer) flavor.

Finally, to observe the relationships between these chemical properties and their predicted targets, partial dependence plots were constructed for the six most important predictors of consumer appreciation 74 , 75 , 76 (Supplementary Fig.  S7 ). One-way partial dependence plots show how a change in concentration affects the predicted appreciation. These plots reveal an important limitation of our models: appreciation predictions remain constant at ever-increasing concentrations. This implies that once a threshold concentration is reached, further increasing the concentration does not affect appreciation. This is false, as it is well-documented that certain compounds become unpleasant at high concentrations, including ethyl acetate (‘nail polish’) 77 and methanethiol (‘sulfury’ and ‘rotten cabbage’) 78 . The inability of our models to grasp that flavor compounds have optimal levels, above which they become negative, is a consequence of working with commercial beer brands where (off-)flavors are rarely too high to negatively impact the product. The two-way partial dependence plots show how changing the concentration of two compounds influences predicted appreciation, visualizing their interactions (Supplementary Fig.  S7 ). In our case, the top 5 parameters are dominated by additive or synergistic interactions, with high concentrations for both compounds resulting in the highest predicted appreciation.

To assess the robustness of our best-performing models and model predictions, we performed 100 iterations of the GBR, RF and ET models. In general, all iterations of the models yielded similar performance (Supplementary Fig.  S8 ). Moreover, the main predictors (including the top predictors ethanol and ethyl acetate) remained virtually the same, especially for GBR and RF. For the iterations of the ET model, we did observe more variation in the top predictors, which is likely a consequence of the model’s inherent random architecture in combination with co-correlations between certain predictors. However, even in this case, several of the top predictors (ethanol and ethyl acetate) remain unchanged, although their rank in importance changes (Supplementary Fig.  S8 ).

Next, we investigated if a combination of RateBeer and trained panel data into one consolidated dataset would lead to stronger models, under the hypothesis that such a model would suffer less from bias in the datasets. A GBR model was trained to predict appreciation on the combined dataset. This model underperformed compared to the RateBeer model, both in the native case and when including a dataset identifier (R 2  = 0.67, 0.26 and 0.42 respectively). For the latter, the dataset identifier is the most important feature (Supplementary Fig.  S9 ), while most of the feature importance remains unchanged, with ethyl acetate and ethanol ranking highest, like in the original model trained only on RateBeer data. It seems that the large variation in the panel dataset introduces noise, weakening the models’ performances and reliability. In addition, it seems reasonable to assume that both datasets are fundamentally different, with the panel dataset obtained by blind tastings by a trained professional panel.

Lastly, we evaluated whether beer style identifiers would further enhance the model’s performance. A GBR model was trained with parameters that explicitly encoded the styles of the samples. This did not improve model performance (R2 = 0.66 with style information vs R2 = 0.67). The most important chemical features are consistent with the model trained without style information (eg. ethanol and ethyl acetate), and with the exception of the most preferred (strong ale) and least preferred (low/no-alcohol) styles, none of the styles were among the most important features (Supplementary Fig.  S9 , Supplementary Table  S5 and S6 ). This is likely due to a combination of style-specific chemical signatures, such as iso-alpha acids and lactic acid, that implicitly convey style information to the original models, as well as the low number of samples belonging to some styles, making it difficult for the model to learn style-specific patterns. Moreover, beer styles are not rigorously defined, with some styles overlapping in features and some beers being misattributed to a specific style, all of which leads to more noise in models that use style parameters.

Model validation

To test if our predictive models give insight into beer appreciation, we set up experiments aimed at improving existing commercial beers. We specifically selected overall appreciation as the trait to be examined because of its complexity and commercial relevance. Beer flavor comprises a complex bouquet rather than single aromas and tastes 53 . Hence, adding a single compound to the extent that a difference is noticeable may lead to an unbalanced, artificial flavor. Therefore, we evaluated the effect of combinations of compounds. Because Blond beers represent the most extensive style in our dataset, we selected a beer from this style as the starting material for these experiments (Beer 64 in Supplementary Data  1 ).

In the first set of experiments, we adjusted the concentrations of compounds that made up the most important predictors of overall appreciation (ethyl acetate, ethanol, lactic acid, ethyl phenyl acetate) together with correlated compounds (ethyl hexanoate, isoamyl acetate, glycerol), bringing them up to 95 th percentile ethanol-normalized concentrations (Methods) within the Blond group (‘Spiked’ concentration in Fig.  5A ). Compared to controls, the spiked beers were found to have significantly improved overall appreciation among trained panelists, with panelist noting increased intensity of ester flavors, sweetness, alcohol, and body fullness (Fig.  5B ). To disentangle the contribution of ethanol to these results, a second experiment was performed without the addition of ethanol. This resulted in a similar outcome, including increased perception of alcohol and overall appreciation.

Adding the top chemical compounds, identified as best predictors of appreciation by our model, into poorly appreciated beers results in increased appreciation from our trained panel. Results of sensory tests between base beers and those spiked with compounds identified as the best predictors by the model. A Blond and Non/Low-alcohol (0.0% ABV) base beers were brought up to 95th-percentile ethanol-normalized concentrations within each style. B For each sensory attribute, tasters indicated the more intense sample and selected the sample they preferred. The numbers above the bars correspond to the p values that indicate significant changes in perceived flavor (two-sided binomial test: alpha 0.05, n  = 20 or 13).

In a last experiment, we tested whether using the model’s predictions can boost the appreciation of a non-alcoholic beer (beer 223 in Supplementary Data  1 ). Again, the addition of a mixture of predicted compounds (omitting ethanol, in this case) resulted in a significant increase in appreciation, body, ester flavor and sweetness.

Predicting flavor and consumer appreciation from chemical composition is one of the ultimate goals of sensory science. A reliable, systematic and unbiased way to link chemical profiles to flavor and food appreciation would be a significant asset to the food and beverage industry. Such tools would substantially aid in quality control and recipe development, offer an efficient and cost-effective alternative to pilot studies and consumer trials and would ultimately allow food manufacturers to produce superior, tailor-made products that better meet the demands of specific consumer groups more efficiently.

A limited set of studies have previously tried, to varying degrees of success, to predict beer flavor and beer popularity based on (a limited set of) chemical compounds and flavors 79 , 80 . Current sensitive, high-throughput technologies allow measuring an unprecedented number of chemical compounds and properties in a large set of samples, yielding a dataset that can train models that help close the gaps between chemistry and flavor, even for a complex natural product like beer. To our knowledge, no previous research gathered data at this scale (250 samples, 226 chemical parameters, 50 sensory attributes and 5 consumer scores) to disentangle and validate the chemical aspects driving beer preference using various machine-learning techniques. We find that modern machine learning models outperform conventional statistical tools, such as correlations and linear models, and can successfully predict flavor appreciation from chemical composition. This could be attributed to the natural incorporation of interactions and non-linear or discontinuous effects in machine learning models, which are not easily grasped by the linear model architecture. While linear models and partial least squares regression represent the most widespread statistical approaches in sensory science, in part because they allow interpretation 65 , 81 , 82 , modern machine learning methods allow for building better predictive models while preserving the possibility to dissect and exploit the underlying patterns. Of the 10 different models we trained, tree-based models, such as our best performing GBR, showed the best overall performance in predicting sensory responses from chemical information, outcompeting artificial neural networks. This agrees with previous reports for models trained on tabular data 83 . Our results are in line with the findings of Colantonio et al. who also identified the gradient boosting architecture as performing best at predicting appreciation and flavor (of tomatoes and blueberries, in their specific study) 26 . Importantly, besides our larger experimental scale, we were able to directly confirm our models’ predictions in vivo.

Our study confirms that flavor compound concentration does not always correlate with perception, suggesting complex interactions that are often missed by more conventional statistics and simple models. Specifically, we find that tree-based algorithms may perform best in developing models that link complex food chemistry with aroma. Furthermore, we show that massive datasets of untrained consumer reviews provide a valuable source of data, that can complement or even replace trained tasting panels, especially for appreciation and basic flavors, such as sweetness and bitterness. This holds despite biases that are known to occur in such datasets, such as price or conformity bias. Moreover, GBR models predict taste better than aroma. This is likely because taste (e.g. bitterness) often directly relates to the corresponding chemical measurements (e.g., iso-alpha acids), whereas such a link is less clear for aromas, which often result from the interplay between multiple volatile compounds. We also find that our models are best at predicting acidity and alcohol, likely because there is a direct relation between the measured chemical compounds (acids and ethanol) and the corresponding perceived sensorial attribute (acidity and alcohol), and because even untrained consumers are generally able to recognize these flavors and aromas.

The predictions of our final models, trained on review data, hold even for blind tastings with small groups of trained tasters, as demonstrated by our ability to validate specific compounds as drivers of beer flavor and appreciation. Since adding a single compound to the extent of a noticeable difference may result in an unbalanced flavor profile, we specifically tested our identified key drivers as a combination of compounds. While this approach does not allow us to validate if a particular single compound would affect flavor and/or appreciation, our experiments do show that this combination of compounds increases consumer appreciation.

It is important to stress that, while it represents an important step forward, our approach still has several major limitations. A key weakness of the GBR model architecture is that amongst co-correlating variables, the largest main effect is consistently preferred for model building. As a result, co-correlating variables often have artificially low importance scores, both for impurity and SHAP-based methods, like we observed in the comparison to the more randomized Extra Trees models. This implies that chemicals identified as key drivers of a specific sensory feature by GBR might not be the true causative compounds, but rather co-correlate with the actual causative chemical. For example, the high importance of ethyl acetate could be (partially) attributed to the total ester content, ethanol or ethyl hexanoate (rho=0.77, rho=0.72 and rho=0.68), while ethyl phenylacetate could hide the importance of prenyl isobutyrate and ethyl benzoate (rho=0.77 and rho=0.76). Expanding our GBR model to include beer style as a parameter did not yield additional power or insight. This is likely due to style-specific chemical signatures, such as iso-alpha acids and lactic acid, that implicitly convey style information to the original model, as well as the smaller sample size per style, limiting the power to uncover style-specific patterns. This can be partly attributed to the curse of dimensionality, where the high number of parameters results in the models mainly incorporating single parameter effects, rather than complex interactions such as style-dependent effects 67 . A larger number of samples may overcome some of these limitations and offer more insight into style-specific effects. On the other hand, beer style is not a rigid scientific classification, and beers within one style often differ a lot, which further complicates the analysis of style as a model factor.

Our study is limited to beers from Belgian breweries. Although these beers cover a large portion of the beer styles available globally, some beer styles and consumer patterns may be missing, while other features might be overrepresented. For example, many Belgian ales exhibit yeast-driven flavor profiles, which is reflected in the chemical drivers of appreciation discovered by this study. In future work, expanding the scope to include diverse markets and beer styles could lead to the identification of even more drivers of appreciation and better models for special niche products that were not present in our beer set.

In addition to inherent limitations of GBR models, there are also some limitations associated with studying food aroma. Even if our chemical analyses measured most of the known aroma compounds, the total number of flavor compounds in complex foods like beer is still larger than the subset we were able to measure in this study. For example, hop-derived thiols, that influence flavor at very low concentrations, are notoriously difficult to measure in a high-throughput experiment. Moreover, consumer perception remains subjective and prone to biases that are difficult to avoid. It is also important to stress that the models are still immature and that more extensive datasets will be crucial for developing more complete models in the future. Besides more samples and parameters, our dataset does not include any demographic information about the tasters. Including such data could lead to better models that grasp external factors like age and culture. Another limitation is that our set of beers consists of high-quality end-products and lacks beers that are unfit for sale, which limits the current model in accurately predicting products that are appreciated very badly. Finally, while models could be readily applied in quality control, their use in sensory science and product development is restrained by their inability to discern causal relationships. Given that the models cannot distinguish compounds that genuinely drive consumer perception from those that merely correlate, validation experiments are essential to identify true causative compounds.

Despite the inherent limitations, dissection of our models enabled us to pinpoint specific molecules as potential drivers of beer aroma and consumer appreciation, including compounds that were unexpected and would not have been identified using standard approaches. Important drivers of beer appreciation uncovered by our models include protein levels, ethyl acetate, ethyl phenyl acetate and lactic acid. Currently, many brewers already use lactic acid to acidify their brewing water and ensure optimal pH for enzymatic activity during the mashing process. Our results suggest that adding lactic acid can also improve beer appreciation, although its individual effect remains to be tested. Interestingly, ethanol appears to be unnecessary to improve beer appreciation, both for blond beer and alcohol-free beer. Given the growing consumer interest in alcohol-free beer, with a predicted annual market growth of >7% 84 , it is relevant for brewers to know what compounds can further increase consumer appreciation of these beers. Hence, our model may readily provide avenues to further improve the flavor and consumer appreciation of both alcoholic and non-alcoholic beers, which is generally considered one of the key challenges for future beer production.

Whereas we see a direct implementation of our results for the development of superior alcohol-free beverages and other food products, our study can also serve as a stepping stone for the development of novel alcohol-containing beverages. We want to echo the growing body of scientific evidence for the negative effects of alcohol consumption, both on the individual level by the mutagenic, teratogenic and carcinogenic effects of ethanol 85 , 86 , as well as the burden on society caused by alcohol abuse and addiction. We encourage the use of our results for the production of healthier, tastier products, including novel and improved beverages with lower alcohol contents. Furthermore, we strongly discourage the use of these technologies to improve the appreciation or addictive properties of harmful substances.

The present work demonstrates that despite some important remaining hurdles, combining the latest developments in chemical analyses, sensory analysis and modern machine learning methods offers exciting avenues for food chemistry and engineering. Soon, these tools may provide solutions in quality control and recipe development, as well as new approaches to sensory science and flavor research.

Beer selection

250 commercial Belgian beers were selected to cover the broad diversity of beer styles and corresponding diversity in chemical composition and aroma. See Supplementary Fig.  S1 .

Chemical dataset

Sample preparation.

Beers within their expiration date were purchased from commercial retailers. Samples were prepared in biological duplicates at room temperature, unless explicitly stated otherwise. Bottle pressure was measured with a manual pressure device (Steinfurth Mess-Systeme GmbH) and used to calculate CO 2 concentration. The beer was poured through two filter papers (Macherey-Nagel, 500713032 MN 713 ¼) to remove carbon dioxide and prevent spontaneous foaming. Samples were then prepared for measurements by targeted Headspace-Gas Chromatography-Flame Ionization Detector/Flame Photometric Detector (HS-GC-FID/FPD), Headspace-Solid Phase Microextraction-Gas Chromatography-Mass Spectrometry (HS-SPME-GC-MS), colorimetric analysis, enzymatic analysis, Near-Infrared (NIR) analysis, as described in the sections below. The mean values of biological duplicates are reported for each compound.

HS-GC-FID/FPD

HS-GC-FID/FPD (Shimadzu GC 2010 Plus) was used to measure higher alcohols, acetaldehyde, esters, 4-vinyl guaicol, and sulfur compounds. Each measurement comprised 5 ml of sample pipetted into a 20 ml glass vial containing 1.75 g NaCl (VWR, 27810.295). 100 µl of 2-heptanol (Sigma-Aldrich, H3003) (internal standard) solution in ethanol (Fisher Chemical, E/0650DF/C17) was added for a final concentration of 2.44 mg/L. Samples were flushed with nitrogen for 10 s, sealed with a silicone septum, stored at −80 °C and analyzed in batches of 20.

The GC was equipped with a DB-WAXetr column (length, 30 m; internal diameter, 0.32 mm; layer thickness, 0.50 µm; Agilent Technologies, Santa Clara, CA, USA) to the FID and an HP-5 column (length, 30 m; internal diameter, 0.25 mm; layer thickness, 0.25 µm; Agilent Technologies, Santa Clara, CA, USA) to the FPD. N 2 was used as the carrier gas. Samples were incubated for 20 min at 70 °C in the headspace autosampler (Flow rate, 35 cm/s; Injection volume, 1000 µL; Injection mode, split; Combi PAL autosampler, CTC analytics, Switzerland). The injector, FID and FPD temperatures were kept at 250 °C. The GC oven temperature was first held at 50 °C for 5 min and then allowed to rise to 80 °C at a rate of 5 °C/min, followed by a second ramp of 4 °C/min until 200 °C kept for 3 min and a final ramp of (4 °C/min) until 230 °C for 1 min. Results were analyzed with the GCSolution software version 2.4 (Shimadzu, Kyoto, Japan). The GC was calibrated with a 5% EtOH solution (VWR International) containing the volatiles under study (Supplementary Table  S7 ).

HS-SPME-GC-MS

HS-SPME-GC-MS (Shimadzu GCMS-QP-2010 Ultra) was used to measure additional volatile compounds, mainly comprising terpenoids and esters. Samples were analyzed by HS-SPME using a triphase DVB/Carboxen/PDMS 50/30 μm SPME fiber (Supelco Co., Bellefonte, PA, USA) followed by gas chromatography (Thermo Fisher Scientific Trace 1300 series, USA) coupled to a mass spectrometer (Thermo Fisher Scientific ISQ series MS) equipped with a TriPlus RSH autosampler. 5 ml of degassed beer sample was placed in 20 ml vials containing 1.75 g NaCl (VWR, 27810.295). 5 µl internal standard mix was added, containing 2-heptanol (1 g/L) (Sigma-Aldrich, H3003), 4-fluorobenzaldehyde (1 g/L) (Sigma-Aldrich, 128376), 2,3-hexanedione (1 g/L) (Sigma-Aldrich, 144169) and guaiacol (1 g/L) (Sigma-Aldrich, W253200) in ethanol (Fisher Chemical, E/0650DF/C17). Each sample was incubated at 60 °C in the autosampler oven with constant agitation. After 5 min equilibration, the SPME fiber was exposed to the sample headspace for 30 min. The compounds trapped on the fiber were thermally desorbed in the injection port of the chromatograph by heating the fiber for 15 min at 270 °C.

The GC-MS was equipped with a low polarity RXi-5Sil MS column (length, 20 m; internal diameter, 0.18 mm; layer thickness, 0.18 µm; Restek, Bellefonte, PA, USA). Injection was performed in splitless mode at 320 °C, a split flow of 9 ml/min, a purge flow of 5 ml/min and an open valve time of 3 min. To obtain a pulsed injection, a programmed gas flow was used whereby the helium gas flow was set at 2.7 mL/min for 0.1 min, followed by a decrease in flow of 20 ml/min to the normal 0.9 mL/min. The temperature was first held at 30 °C for 3 min and then allowed to rise to 80 °C at a rate of 7 °C/min, followed by a second ramp of 2 °C/min till 125 °C and a final ramp of 8 °C/min with a final temperature of 270 °C.

Mass acquisition range was 33 to 550 amu at a scan rate of 5 scans/s. Electron impact ionization energy was 70 eV. The interface and ion source were kept at 275 °C and 250 °C, respectively. A mix of linear n-alkanes (from C7 to C40, Supelco Co.) was injected into the GC-MS under identical conditions to serve as external retention index markers. Identification and quantification of the compounds were performed using an in-house developed R script as described in Goelen et al. and Reher et al. 87 , 88 (for package information, see Supplementary Table  S8 ). Briefly, chromatograms were analyzed using AMDIS (v2.71) 89 to separate overlapping peaks and obtain pure compound spectra. The NIST MS Search software (v2.0 g) in combination with the NIST2017, FFNSC3 and Adams4 libraries were used to manually identify the empirical spectra, taking into account the expected retention time. After background subtraction and correcting for retention time shifts between samples run on different days based on alkane ladders, compound elution profiles were extracted and integrated using a file with 284 target compounds of interest, which were either recovered in our identified AMDIS list of spectra or were known to occur in beer. Compound elution profiles were estimated for every peak in every chromatogram over a time-restricted window using weighted non-negative least square analysis after which peak areas were integrated 87 , 88 . Batch effect correction was performed by normalizing against the most stable internal standard compound, 4-fluorobenzaldehyde. Out of all 284 target compounds that were analyzed, 167 were visually judged to have reliable elution profiles and were used for final analysis.

Discrete photometric and enzymatic analysis

Discrete photometric and enzymatic analysis (Thermo Scientific TM Gallery TM Plus Beermaster Discrete Analyzer) was used to measure acetic acid, ammonia, beta-glucan, iso-alpha acids, color, sugars, glycerol, iron, pH, protein, and sulfite. 2 ml of sample volume was used for the analyses. Information regarding the reagents and standard solutions used for analyses and calibrations is included in Supplementary Table  S7 and Supplementary Table  S9 .

NIR analyses

NIR analysis (Anton Paar Alcolyzer Beer ME System) was used to measure ethanol. Measurements comprised 50 ml of sample, and a 10% EtOH solution was used for calibration.

Correlation calculations

Pairwise Spearman Rank correlations were calculated between all chemical properties.

Sensory dataset

Trained panel.

Our trained tasting panel consisted of volunteers who gave prior verbal informed consent. All compounds used for the validation experiment were of food-grade quality. The tasting sessions were approved by the Social and Societal Ethics Committee of the KU Leuven (G-2022-5677-R2(MAR)). All online reviewers agreed to the Terms and Conditions of the RateBeer website.

Sensory analysis was performed according to the American Society of Brewing Chemists (ASBC) Sensory Analysis Methods 90 . 30 volunteers were screened through a series of triangle tests. The sixteen most sensitive and consistent tasters were retained as taste panel members. The resulting panel was diverse in age [22–42, mean: 29], sex [56% male] and nationality [7 different countries]. The panel developed a consensus vocabulary to describe beer aroma, taste and mouthfeel. Panelists were trained to identify and score 50 different attributes, using a 7-point scale to rate attributes’ intensity. The scoring sheet is included as Supplementary Data  3 . Sensory assessments took place between 10–12 a.m. The beers were served in black-colored glasses. Per session, between 5 and 12 beers of the same style were tasted at 12 °C to 16 °C. Two reference beers were added to each set and indicated as ‘Reference 1 & 2’, allowing panel members to calibrate their ratings. Not all panelists were present at every tasting. Scores were scaled by standard deviation and mean-centered per taster. Values are represented as z-scores and clustered by Euclidean distance. Pairwise Spearman correlations were calculated between taste and aroma sensory attributes. Panel consistency was evaluated by repeating samples on different sessions and performing ANOVA to identify differences, using the ‘stats’ package (v4.2.2) in R (for package information, see Supplementary Table  S8 ).

Online reviews from a public database

The ‘scrapy’ package in Python (v3.6) (for package information, see Supplementary Table  S8 ). was used to collect 232,288 online reviews (mean=922, min=6, max=5343) from RateBeer, an online beer review database. Each review entry comprised 5 numerical scores (appearance, aroma, taste, palate and overall quality) and an optional review text. The total number of reviews per reviewer was collected separately. Numerical scores were scaled and centered per rater, and mean scores were calculated per beer.

For the review texts, the language was estimated using the packages ‘langdetect’ and ‘langid’ in Python. Reviews that were classified as English by both packages were kept. Reviewers with fewer than 100 entries overall were discarded. 181,025 reviews from >6000 reviewers from >40 countries remained. Text processing was done using the ‘nltk’ package in Python. Texts were corrected for slang and misspellings; proper nouns and rare words that are relevant to the beer context were specified and kept as-is (‘Chimay’,’Lambic’, etc.). A dictionary of semantically similar sensorial terms, for example ‘floral’ and ‘flower’, was created and collapsed together into one term. Words were stemmed and lemmatized to avoid identifying words such as ‘acid’ and ‘acidity’ as separate terms. Numbers and punctuation were removed.

Sentences from up to 50 randomly chosen reviews per beer were manually categorized according to the aspect of beer they describe (appearance, aroma, taste, palate, overall quality—not to be confused with the 5 numerical scores described above) or flagged as irrelevant if they contained no useful information. If a beer contained fewer than 50 reviews, all reviews were manually classified. This labeled data set was used to train a model that classified the rest of the sentences for all beers 91 . Sentences describing taste and aroma were extracted, and term frequency–inverse document frequency (TFIDF) was implemented to calculate enrichment scores for sensorial words per beer.

The sex of the tasting subject was not considered when building our sensory database. Instead, results from different panelists were averaged, both for our trained panel (56% male, 44% female) and the RateBeer reviews (70% male, 30% female for RateBeer as a whole).

Beer price collection and processing

Beer prices were collected from the following stores: Colruyt, Delhaize, Total Wine, BeerHawk, The Belgian Beer Shop, The Belgian Shop, and Beer of Belgium. Where applicable, prices were converted to Euros and normalized per liter. Spearman correlations were calculated between these prices and mean overall appreciation scores from RateBeer and the taste panel, respectively.

Pairwise Spearman Rank correlations were calculated between all sensory properties.

Machine learning models

Predictive modeling of sensory profiles from chemical data.

Regression models were constructed to predict (a) trained panel scores for beer flavors and quality from beer chemical profiles and (b) public reviews’ appreciation scores from beer chemical profiles. Z-scores were used to represent sensory attributes in both data sets. Chemical properties with log-normal distributions (Shapiro-Wilk test, p  <  0.05 ) were log-transformed. Missing chemical measurements (0.1% of all data) were replaced with mean values per attribute. Observations from 250 beers were randomly separated into a training set (70%, 175 beers) and a test set (30%, 75 beers), stratified per beer style. Chemical measurements (p = 231) were normalized based on the training set average and standard deviation. In total, three linear regression-based models: linear regression with first-order interaction terms (LR), lasso regression with first-order interaction terms (Lasso) and partial least squares regression (PLSR); five decision tree models, Adaboost regressor (ABR), Extra Trees (ET), Gradient Boosting regressor (GBR), Random Forest (RF) and XGBoost regressor (XGBR); one support vector machine model (SVR) and one artificial neural network model (ANN) were trained. The models were implemented using the ‘scikit-learn’ package (v1.2.2) and ‘xgboost’ package (v1.7.3) in Python (v3.9.16). Models were trained, and hyperparameters optimized, using five-fold cross-validated grid search with the coefficient of determination (R 2 ) as the evaluation metric. The ANN (scikit-learn’s MLPRegressor) was optimized using Bayesian Tree-Structured Parzen Estimator optimization with the ‘Optuna’ Python package (v3.2.0). Individual models were trained per attribute, and a multi-output model was trained on all attributes simultaneously.

Model dissection

GBR was found to outperform other methods, resulting in models with the highest average R 2 values in both trained panel and public review data sets. Impurity-based rankings of the most important predictors for each predicted sensorial trait were obtained using the ‘scikit-learn’ package. To observe the relationships between these chemical properties and their predicted targets, partial dependence plots (PDP) were constructed for the six most important predictors of consumer appreciation 74 , 75 .

The ‘SHAP’ package in Python (v0.41.0) was implemented to provide an alternative ranking of predictor importance and to visualize the predictors’ effects as a function of their concentration 68 .

Validation of causal chemical properties

To validate the effects of the most important model features on predicted sensory attributes, beers were spiked with the chemical compounds identified by the models and descriptive sensory analyses were carried out according to the American Society of Brewing Chemists (ASBC) protocol 90 .

Compound spiking was done 30 min before tasting. Compounds were spiked into fresh beer bottles, that were immediately resealed and inverted three times. Fresh bottles of beer were opened for the same duration, resealed, and inverted thrice, to serve as controls. Pairs of spiked samples and controls were served simultaneously, chilled and in dark glasses as outlined in the Trained panel section above. Tasters were instructed to select the glass with the higher flavor intensity for each attribute (directional difference test 92 ) and to select the glass they prefer.

The final concentration after spiking was equal to the within-style average, after normalizing by ethanol concentration. This was done to ensure balanced flavor profiles in the final spiked beer. The same methods were applied to improve a non-alcoholic beer. Compounds were the following: ethyl acetate (Merck KGaA, W241415), ethyl hexanoate (Merck KGaA, W243906), isoamyl acetate (Merck KGaA, W205508), phenethyl acetate (Merck KGaA, W285706), ethanol (96%, Colruyt), glycerol (Merck KGaA, W252506), lactic acid (Merck KGaA, 261106).

Significant differences in preference or perceived intensity were determined by performing the two-sided binomial test on each attribute.

Reporting summary

Further information on research design is available in the  Nature Portfolio Reporting Summary linked to this article.

Data availability

The data that support the findings of this work are available in the Supplementary Data files and have been deposited to Zenodo under accession code 10653704 93 . The RateBeer scores data are under restricted access, they are not publicly available as they are property of RateBeer (ZX Ventures, USA). Access can be obtained from the authors upon reasonable request and with permission of RateBeer (ZX Ventures, USA).  Source data are provided with this paper.

Code availability

The code for training the machine learning models, analyzing the models, and generating the figures has been deposited to Zenodo under accession code 10653704 93 .

Tieman, D. et al. A chemical genetic roadmap to improved tomato flavor. Science 355 , 391–394 (2017).

Article   ADS   CAS   PubMed   Google Scholar  

Plutowska, B. & Wardencki, W. Application of gas chromatography–olfactometry (GC–O) in analysis and quality assessment of alcoholic beverages – A review. Food Chem. 107 , 449–463 (2008).

Article   CAS   Google Scholar  

Legin, A., Rudnitskaya, A., Seleznev, B. & Vlasov, Y. Electronic tongue for quality assessment of ethanol, vodka and eau-de-vie. Anal. Chim. Acta 534 , 129–135 (2005).

Loutfi, A., Coradeschi, S., Mani, G. K., Shankar, P. & Rayappan, J. B. B. Electronic noses for food quality: A review. J. Food Eng. 144 , 103–111 (2015).

Ahn, Y.-Y., Ahnert, S. E., Bagrow, J. P. & Barabási, A.-L. Flavor network and the principles of food pairing. Sci. Rep. 1 , 196 (2011).

Article   CAS   PubMed   PubMed Central   Google Scholar  

Bartoshuk, L. M. & Klee, H. J. Better fruits and vegetables through sensory analysis. Curr. Biol. 23 , R374–R378 (2013).

Article   CAS   PubMed   Google Scholar  

Piggott, J. R. Design questions in sensory and consumer science. Food Qual. Prefer. 3293 , 217–220 (1995).

Article   Google Scholar  

Kermit, M. & Lengard, V. Assessing the performance of a sensory panel-panellist monitoring and tracking. J. Chemom. 19 , 154–161 (2005).

Cook, D. J., Hollowood, T. A., Linforth, R. S. T. & Taylor, A. J. Correlating instrumental measurements of texture and flavour release with human perception. Int. J. Food Sci. Technol. 40 , 631–641 (2005).

Chinchanachokchai, S., Thontirawong, P. & Chinchanachokchai, P. A tale of two recommender systems: The moderating role of consumer expertise on artificial intelligence based product recommendations. J. Retail. Consum. Serv. 61 , 1–12 (2021).

Ross, C. F. Sensory science at the human-machine interface. Trends Food Sci. Technol. 20 , 63–72 (2009).

Chambers, E. IV & Koppel, K. Associations of volatile compounds with sensory aroma and flavor: The complex nature of flavor. Molecules 18 , 4887–4905 (2013).

Pinu, F. R. Metabolomics—The new frontier in food safety and quality research. Food Res. Int. 72 , 80–81 (2015).

Danezis, G. P., Tsagkaris, A. S., Brusic, V. & Georgiou, C. A. Food authentication: state of the art and prospects. Curr. Opin. Food Sci. 10 , 22–31 (2016).

Shepherd, G. M. Smell images and the flavour system in the human brain. Nature 444 , 316–321 (2006).

Meilgaard, M. C. Prediction of flavor differences between beers from their chemical composition. J. Agric. Food Chem. 30 , 1009–1017 (1982).

Xu, L. et al. Widespread receptor-driven modulation in peripheral olfactory coding. Science 368 , eaaz5390 (2020).

Kupferschmidt, K. Following the flavor. Science 340 , 808–809 (2013).

Billesbølle, C. B. et al. Structural basis of odorant recognition by a human odorant receptor. Nature 615 , 742–749 (2023).

Article   ADS   PubMed   PubMed Central   Google Scholar  

Smith, B. Perspective: Complexities of flavour. Nature 486 , S6–S6 (2012).

Pfister, P. et al. Odorant receptor inhibition is fundamental to odor encoding. Curr. Biol. 30 , 2574–2587 (2020).

Moskowitz, H. W., Kumaraiah, V., Sharma, K. N., Jacobs, H. L. & Sharma, S. D. Cross-cultural differences in simple taste preferences. Science 190 , 1217–1218 (1975).

Eriksson, N. et al. A genetic variant near olfactory receptor genes influences cilantro preference. Flavour 1 , 22 (2012).

Ferdenzi, C. et al. Variability of affective responses to odors: Culture, gender, and olfactory knowledge. Chem. Senses 38 , 175–186 (2013).

Article   PubMed   Google Scholar  

Lawless, H. T. & Heymann, H. Sensory evaluation of food: Principles and practices. (Springer, New York, NY). https://doi.org/10.1007/978-1-4419-6488-5 (2010).

Colantonio, V. et al. Metabolomic selection for enhanced fruit flavor. Proc. Natl. Acad. Sci. 119 , e2115865119 (2022).

Fritz, F., Preissner, R. & Banerjee, P. VirtualTaste: a web server for the prediction of organoleptic properties of chemical compounds. Nucleic Acids Res 49 , W679–W684 (2021).

Tuwani, R., Wadhwa, S. & Bagler, G. BitterSweet: Building machine learning models for predicting the bitter and sweet taste of small molecules. Sci. Rep. 9 , 1–13 (2019).

Dagan-Wiener, A. et al. Bitter or not? BitterPredict, a tool for predicting taste from chemical structure. Sci. Rep. 7 , 1–13 (2017).

Pallante, L. et al. Toward a general and interpretable umami taste predictor using a multi-objective machine learning approach. Sci. Rep. 12 , 1–11 (2022).

Malavolta, M. et al. A survey on computational taste predictors. Eur. Food Res. Technol. 248 , 2215–2235 (2022).

Lee, B. K. et al. A principal odor map unifies diverse tasks in olfactory perception. Science 381 , 999–1006 (2023).

Mayhew, E. J. et al. Transport features predict if a molecule is odorous. Proc. Natl. Acad. Sci. 119 , e2116576119 (2022).

Niu, Y. et al. Sensory evaluation of the synergism among ester odorants in light aroma-type liquor by odor threshold, aroma intensity and flash GC electronic nose. Food Res. Int. 113 , 102–114 (2018).

Yu, P., Low, M. Y. & Zhou, W. Design of experiments and regression modelling in food flavour and sensory analysis: A review. Trends Food Sci. Technol. 71 , 202–215 (2018).

Oladokun, O. et al. The impact of hop bitter acid and polyphenol profiles on the perceived bitterness of beer. Food Chem. 205 , 212–220 (2016).

Linforth, R., Cabannes, M., Hewson, L., Yang, N. & Taylor, A. Effect of fat content on flavor delivery during consumption: An in vivo model. J. Agric. Food Chem. 58 , 6905–6911 (2010).

Guo, S., Na Jom, K. & Ge, Y. Influence of roasting condition on flavor profile of sunflower seeds: A flavoromics approach. Sci. Rep. 9 , 11295 (2019).

Ren, Q. et al. The changes of microbial community and flavor compound in the fermentation process of Chinese rice wine using Fagopyrum tataricum grain as feedstock. Sci. Rep. 9 , 3365 (2019).

Hastie, T., Friedman, J. & Tibshirani, R. The Elements of Statistical Learning. (Springer, New York, NY). https://doi.org/10.1007/978-0-387-21606-5 (2001).

Dietz, C., Cook, D., Huismann, M., Wilson, C. & Ford, R. The multisensory perception of hop essential oil: a review. J. Inst. Brew. 126 , 320–342 (2020).

CAS   Google Scholar  

Roncoroni, Miguel & Verstrepen, Kevin Joan. Belgian Beer: Tested and Tasted. (Lannoo, 2018).

Meilgaard, M. Flavor chemistry of beer: Part II: Flavor and threshold of 239 aroma volatiles. in (1975).

Bokulich, N. A. & Bamforth, C. W. The microbiology of malting and brewing. Microbiol. Mol. Biol. Rev. MMBR 77 , 157–172 (2013).

Dzialo, M. C., Park, R., Steensels, J., Lievens, B. & Verstrepen, K. J. Physiology, ecology and industrial applications of aroma formation in yeast. FEMS Microbiol. Rev. 41 , S95–S128 (2017).

Article   PubMed   PubMed Central   Google Scholar  

Datta, A. et al. Computer-aided food engineering. Nat. Food 3 , 894–904 (2022).

American Society of Brewing Chemists. Beer Methods. (American Society of Brewing Chemists, St. Paul, MN, U.S.A.).

Olaniran, A. O., Hiralal, L., Mokoena, M. P. & Pillay, B. Flavour-active volatile compounds in beer: production, regulation and control. J. Inst. Brew. 123 , 13–23 (2017).

Verstrepen, K. J. et al. Flavor-active esters: Adding fruitiness to beer. J. Biosci. Bioeng. 96 , 110–118 (2003).

Meilgaard, M. C. Flavour chemistry of beer. part I: flavour interaction between principal volatiles. Master Brew. Assoc. Am. Tech. Q 12 , 107–117 (1975).

Briggs, D. E., Boulton, C. A., Brookes, P. A. & Stevens, R. Brewing 227–254. (Woodhead Publishing). https://doi.org/10.1533/9781855739062.227 (2004).

Bossaert, S., Crauwels, S., De Rouck, G. & Lievens, B. The power of sour - A review: Old traditions, new opportunities. BrewingScience 72 , 78–88 (2019).

Google Scholar  

Verstrepen, K. J. et al. Flavor active esters: Adding fruitiness to beer. J. Biosci. Bioeng. 96 , 110–118 (2003).

Snauwaert, I. et al. Microbial diversity and metabolite composition of Belgian red-brown acidic ales. Int. J. Food Microbiol. 221 , 1–11 (2016).

Spitaels, F. et al. The microbial diversity of traditional spontaneously fermented lambic beer. PLoS ONE 9 , e95384 (2014).

Blanco, C. A., Andrés-Iglesias, C. & Montero, O. Low-alcohol Beers: Flavor Compounds, Defects, and Improvement Strategies. Crit. Rev. Food Sci. Nutr. 56 , 1379–1388 (2016).

Jackowski, M. & Trusek, A. Non-Alcohol. beer Prod. – Overv. 20 , 32–38 (2018).

Takoi, K. et al. The contribution of geraniol metabolism to the citrus flavour of beer: Synergy of geraniol and β-citronellol under coexistence with excess linalool. J. Inst. Brew. 116 , 251–260 (2010).

Kroeze, J. H. & Bartoshuk, L. M. Bitterness suppression as revealed by split-tongue taste stimulation in humans. Physiol. Behav. 35 , 779–783 (1985).

Mennella, J. A. et al. A spoonful of sugar helps the medicine go down”: Bitter masking bysucrose among children and adults. Chem. Senses 40 , 17–25 (2015).

Wietstock, P., Kunz, T., Perreira, F. & Methner, F.-J. Metal chelation behavior of hop acids in buffered model systems. BrewingScience 69 , 56–63 (2016).

Sancho, D., Blanco, C. A., Caballero, I. & Pascual, A. Free iron in pale, dark and alcohol-free commercial lager beers. J. Sci. Food Agric. 91 , 1142–1147 (2011).

Rodrigues, H. & Parr, W. V. Contribution of cross-cultural studies to understanding wine appreciation: A review. Food Res. Int. 115 , 251–258 (2019).

Korneva, E. & Blockeel, H. Towards better evaluation of multi-target regression models. in ECML PKDD 2020 Workshops (eds. Koprinska, I. et al.) 353–362 (Springer International Publishing, Cham, 2020). https://doi.org/10.1007/978-3-030-65965-3_23 .

Gastón Ares. Mathematical and Statistical Methods in Food Science and Technology. (Wiley, 2013).

Grinsztajn, L., Oyallon, E. & Varoquaux, G. Why do tree-based models still outperform deep learning on tabular data? Preprint at http://arxiv.org/abs/2207.08815 (2022).

Gries, S. T. Statistics for Linguistics with R: A Practical Introduction. in Statistics for Linguistics with R (De Gruyter Mouton, 2021). https://doi.org/10.1515/9783110718256 .

Lundberg, S. M. et al. From local explanations to global understanding with explainable AI for trees. Nat. Mach. Intell. 2 , 56–67 (2020).

Ickes, C. M. & Cadwallader, K. R. Effects of ethanol on flavor perception in alcoholic beverages. Chemosens. Percept. 10 , 119–134 (2017).

Kato, M. et al. Influence of high molecular weight polypeptides on the mouthfeel of commercial beer. J. Inst. Brew. 127 , 27–40 (2021).

Wauters, R. et al. Novel Saccharomyces cerevisiae variants slow down the accumulation of staling aldehydes and improve beer shelf-life. Food Chem. 398 , 1–11 (2023).

Li, H., Jia, S. & Zhang, W. Rapid determination of low-level sulfur compounds in beer by headspace gas chromatography with a pulsed flame photometric detector. J. Am. Soc. Brew. Chem. 66 , 188–191 (2008).

Dercksen, A., Laurens, J., Torline, P., Axcell, B. C. & Rohwer, E. Quantitative analysis of volatile sulfur compounds in beer using a membrane extraction interface. J. Am. Soc. Brew. Chem. 54 , 228–233 (1996).

Molnar, C. Interpretable Machine Learning: A Guide for Making Black-Box Models Interpretable. (2020).

Zhao, Q. & Hastie, T. Causal interpretations of black-box models. J. Bus. Econ. Stat. Publ. Am. Stat. Assoc. 39 , 272–281 (2019).

Article   MathSciNet   Google Scholar  

Hastie, T., Tibshirani, R. & Friedman, J. The Elements of Statistical Learning. (Springer, 2019).

Labrado, D. et al. Identification by NMR of key compounds present in beer distillates and residual phases after dealcoholization by vacuum distillation. J. Sci. Food Agric. 100 , 3971–3978 (2020).

Lusk, L. T., Kay, S. B., Porubcan, A. & Ryder, D. S. Key olfactory cues for beer oxidation. J. Am. Soc. Brew. Chem. 70 , 257–261 (2012).

Gonzalez Viejo, C., Torrico, D. D., Dunshea, F. R. & Fuentes, S. Development of artificial neural network models to assess beer acceptability based on sensory properties using a robotic pourer: A comparative model approach to achieve an artificial intelligence system. Beverages 5 , 33 (2019).

Gonzalez Viejo, C., Fuentes, S., Torrico, D. D., Godbole, A. & Dunshea, F. R. Chemical characterization of aromas in beer and their effect on consumers liking. Food Chem. 293 , 479–485 (2019).

Gilbert, J. L. et al. Identifying breeding priorities for blueberry flavor using biochemical, sensory, and genotype by environment analyses. PLOS ONE 10 , 1–21 (2015).

Goulet, C. et al. Role of an esterase in flavor volatile variation within the tomato clade. Proc. Natl. Acad. Sci. 109 , 19009–19014 (2012).

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

Borisov, V. et al. Deep Neural Networks and Tabular Data: A Survey. IEEE Trans. Neural Netw. Learn. Syst. 1–21 https://doi.org/10.1109/TNNLS.2022.3229161 (2022).

Statista. Statista Consumer Market Outlook: Beer - Worldwide.

Seitz, H. K. & Stickel, F. Molecular mechanisms of alcoholmediated carcinogenesis. Nat. Rev. Cancer 7 , 599–612 (2007).

Voordeckers, K. et al. Ethanol exposure increases mutation rate through error-prone polymerases. Nat. Commun. 11 , 3664 (2020).

Goelen, T. et al. Bacterial phylogeny predicts volatile organic compound composition and olfactory response of an aphid parasitoid. Oikos 129 , 1415–1428 (2020).

Article   ADS   Google Scholar  

Reher, T. et al. Evaluation of hop (Humulus lupulus) as a repellent for the management of Drosophila suzukii. Crop Prot. 124 , 104839 (2019).

Stein, S. E. An integrated method for spectrum extraction and compound identification from gas chromatography/mass spectrometry data. J. Am. Soc. Mass Spectrom. 10 , 770–781 (1999).

American Society of Brewing Chemists. Sensory Analysis Methods. (American Society of Brewing Chemists, St. Paul, MN, U.S.A., 1992).

McAuley, J., Leskovec, J. & Jurafsky, D. Learning Attitudes and Attributes from Multi-Aspect Reviews. Preprint at https://doi.org/10.48550/arXiv.1210.3926 (2012).

Meilgaard, M. C., Carr, B. T. & Carr, B. T. Sensory Evaluation Techniques. (CRC Press, Boca Raton). https://doi.org/10.1201/b16452 (2014).

Schreurs, M. et al. Data from: Predicting and improving complex beer flavor through machine learning. Zenodo https://doi.org/10.5281/zenodo.10653704 (2024).

Download references

Acknowledgements

We thank all lab members for their discussions and thank all tasting panel members for their contributions. Special thanks go out to Dr. Karin Voordeckers for her tremendous help in proofreading and improving the manuscript. M.S. was supported by a Baillet-Latour fellowship, L.C. acknowledges financial support from KU Leuven (C16/17/006), F.A.T. was supported by a PhD fellowship from FWO (1S08821N). Research in the lab of K.J.V. is supported by KU Leuven, FWO, VIB, VLAIO and the Brewing Science Serves Health Fund. Research in the lab of T.W. is supported by FWO (G.0A51.15) and KU Leuven (C16/17/006).

Author information

These authors contributed equally: Michiel Schreurs, Supinya Piampongsant, Miguel Roncoroni.

Authors and Affiliations

VIB—KU Leuven Center for Microbiology, Gaston Geenslaan 1, B-3001, Leuven, Belgium

Michiel Schreurs, Supinya Piampongsant, Miguel Roncoroni, Lloyd Cool, Beatriz Herrera-Malaver, Florian A. Theßeling & Kevin J. Verstrepen

CMPG Laboratory of Genetics and Genomics, KU Leuven, Gaston Geenslaan 1, B-3001, Leuven, Belgium

Leuven Institute for Beer Research (LIBR), Gaston Geenslaan 1, B-3001, Leuven, Belgium

Laboratory of Socioecology and Social Evolution, KU Leuven, Naamsestraat 59, B-3000, Leuven, Belgium

Lloyd Cool, Christophe Vanderaa & Tom Wenseleers

VIB Bioinformatics Core, VIB, Rijvisschestraat 120, B-9052, Ghent, Belgium

Łukasz Kreft & Alexander Botzki

AB InBev SA/NV, Brouwerijplein 1, B-3000, Leuven, Belgium

Philippe Malcorps & Luk Daenen

You can also search for this author in PubMed   Google Scholar

Contributions

S.P., M.S. and K.J.V. conceived the experiments. S.P., M.S. and K.J.V. designed the experiments. S.P., M.S., M.R., B.H. and F.A.T. performed the experiments. S.P., M.S., L.C., C.V., L.K., A.B., P.M., L.D., T.W. and K.J.V. contributed analysis ideas. S.P., M.S., L.C., C.V., T.W. and K.J.V. analyzed the data. All authors contributed to writing the manuscript.

Corresponding author

Correspondence to Kevin J. Verstrepen .

Ethics declarations

Competing interests.

K.J.V. is affiliated with bar.on. The other authors declare no competing interests.

Peer review

Peer review information.

Nature Communications thanks Florian Bauer, Andrew John Macintosh and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. A peer review file is available.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary information, peer review file, description of additional supplementary files, supplementary data 1, supplementary data 2, supplementary data 3, supplementary data 4, supplementary data 5, supplementary data 6, supplementary data 7, reporting summary, source data, source data, rights and permissions.

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Schreurs, M., Piampongsant, S., Roncoroni, M. et al. Predicting and improving complex beer flavor through machine learning. Nat Commun 15 , 2368 (2024). https://doi.org/10.1038/s41467-024-46346-0

Download citation

Received : 30 October 2023

Accepted : 21 February 2024

Published : 26 March 2024

DOI : https://doi.org/10.1038/s41467-024-46346-0

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: Translational Research newsletter — top stories in biotechnology, drug discovery and pharma.

• SUGGESTED TOPICS
• The Magazine
• Newsletters
• Managing Yourself
• Managing Teams
• Work-life Balance
• The Big Idea
• Data & Visuals
• Reading Lists
• Case Selections
• HBR Learning
• Topic Feeds
• Account Settings
• Email Preferences

6 Common Leadership Styles — and How to Decide Which to Use When

• Rebecca Knight

Being a great leader means recognizing that different circumstances call for different approaches.

Research suggests that the most effective leaders adapt their style to different circumstances — be it a change in setting, a shift in organizational dynamics, or a turn in the business cycle. But what if you feel like you’re not equipped to take on a new and different leadership style — let alone more than one? In this article, the author outlines the six leadership styles Daniel Goleman first introduced in his 2000 HBR article, “Leadership That Gets Results,” and explains when to use each one. The good news is that personality is not destiny. Even if you’re naturally introverted or you tend to be driven by data and analysis rather than emotion, you can still learn how to adapt different leadership styles to organize, motivate, and direct your team.

Much has been written about common leadership styles and how to identify the right style for you, whether it’s transactional or transformational, bureaucratic or laissez-faire. But according to Daniel Goleman, a psychologist best known for his work on emotional intelligence, “Being a great leader means recognizing that different circumstances may call for different approaches.”

• RK Rebecca Knight is a journalist who writes about all things related to the changing nature of careers and the workplace. Her essays and reported stories have been featured in The Boston Globe, Business Insider, The New York Times, BBC, and The Christian Science Monitor. She was shortlisted as a Reuters Institute Fellow at Oxford University in 2023. Earlier in her career, she spent a decade as an editor and reporter at the Financial Times in New York, London, and Boston.

Partner Center