How to Analyze Open-Ended Survey Responses
min read - Updated on Nov 15, 2026To analyze open-ended survey responses with Kimola, you upload the survey results as a file and create a Report. Kimola groups every answer under the themes it mentions, labels its sentiment and, if you choose, answers research questions about it with Dimensions, such as what goes wrong (Pain Points) and what is missing (Unmet Needs). The columns that come with the answers, such as a customer segment, a region or a score, let you break the results down by group of respondents. The workflow takes five steps and works with the export of any survey tool (.xls, .xlsx, .csv or .tsv) or with a Google Sheets spreadsheet.
The Goal
Open-ended questions collect what a rating can't: the reason behind a score, the problem a respondent ran into, the thing they wished for. Customer experience, product, marketing and research teams ask them in satisfaction, post-purchase, event and employee surveys, and then hold hundreds or thousands of free-text answers that are slow to read and to code by hand.
This guide answers four questions about those answers: which themes respondents mention, how positive or negative they are about each theme, what goes wrong and what is missing, and how the answers differ between groups of respondents. Each step links to the article that describes its feature in full.
What You Need
You need a Kimola account and the results of your survey as a file or a Google Sheets spreadsheet. The file needs one column with the text of the open-ended answers. Columns that describe the respondents, such as a segment, a region or a score, are optional and make Step 5 possible. The Reports, themes, Dimensions, Signals and Action Plans in this guide are available in every package.
Creating a Report spends queries from your package, by the rule queries = rows × models × Dimensions. Step 3 shows how to check the number before anything is analyzed.
Step 1: Export Your Survey
Start from the results of your survey tool. Most survey tools can export responses to an Excel or CSV file, and where the export button is depends on the tool. Kimola accepts .xls, .xlsx, .csv and .tsv files, one file per Report, up to 30 MB.
Lay the file out with the column names in the first row and one respondent in every row below it. Two columns matter to Kimola in a survey file.
Text Column (required): the column with the open-ended answers. Keep the answers of one question in this one column.
Date Column (optional): the date and time each respondent answered. With it, the Report can show how topics change over time, for example from one survey wave to the next.
Kimola doesn't analyze the other columns, but they become filters in the Report. Keep the columns that describe the respondent or the response, such as a rating or NPS score, a customer segment, a product, a region or a survey wave. Step 5 uses them to break the results down by respondent group.
Keep respondent columns such as segment, region, product or score in the file. They become the groups you compare in Step 5.
A Report analyzes one Text Column. When your survey has several open-ended questions, upload the file once for each question and choose a different Text Column each time. Respondents who skipped a question leave its cell empty. Rows with an empty Text Column are left out of the analysis and don't count in queries, so you don't need to delete them.
A hotel group exports its post-stay survey with the columns Guest Comment, Hotel, Stay Type, Submitted On and Rating. Guest Comment is the Text Column and Submitted On is the Date Column. Hotel, Stay Type and Rating stay in the file as filters, so the team can read and compare the comments of each hotel and each kind of stay.
If your responses are already in Google Sheets, for example the response sheet of a Google Forms survey, you can skip the export. Connect Google Sheets and pick the spreadsheet in Google's file picker. It opens in the same report wizard as an uploaded file. The integration is available in the paid packages, not in Starter, and Kimola On-Premises doesn't offer it. Where it isn't available, download the spreadsheet as an .xlsx or .csv file and upload that.
[Screenshot: A survey export opened in a spreadsheet, with the comment column, the date column and the respondent columns]
Step 2: Upload the File
Open Reports in the left menu and drag the file onto the upload area, or click the area and choose the file from your computer. Kimola uploads the file, checks its format, size, readability and data structure, and opens the report wizard on Sheets & Columns.
Choose the Text Column, which holds the open-ended answers. The wizard moves on only after you have chosen it. If your file has a date, also choose the Date Column. When an Excel file has more than one sheet, the preview lists the sheets by name: click the sheet that holds the answers and choose its columns. See Create a Report by Uploading a Custom Dataset for this step in detail.
[Screenshot: The Sheets & Columns step with a Text Column and a Date Column chosen]
Step 3: Choose Classifiers and Dimensions
Three choices decide what the Report tells you about the answers: the classifiers that label each answer, the structure of those labels and the Dimensions that ask research questions of each answer.
Classifiers
In Classifiers, choose the Automatic Classifier and the Sentiment Classifier together. The Automatic Classifier discovers the themes from your answers, so you don't need a list of categories in advance. The Sentiment Classifier labels each answer as positive, negative or none. A content classifier and the Sentiment Classifier together give the Report its themes with their sentiment, and the best and worst performing themes need both.
If your team already codes the survey with a fixed set of topics, a custom model with those topics can take the place of the Automatic Classifier. Custom models are available in the paid packages, not in Starter.
[Screenshot: The Classifiers step with the Automatic Classifier and the Sentiment Classifier chosen]
Structure
In Structure, turn on Enable Multi-label Classification for open-ended answers. One answer often mentions several things, such as the price and the delivery time, and with multi-label classification it is counted under each of them. Without it, each answer is grouped under one main theme. Because one answer can carry several labels, the shares of a Report's themes can add up to more than 100%. See Create a Report Using Multi-Label Classification.
Dimensions
Dimensions are optional, and they turn the answers into research findings. For survey answers, start with Pain Points ("What goes wrong or creates difficulty?") and Unmet Needs ("What is missing or desired?"). Pain Points collect what respondents struggle with or complain about, and Unmet Needs collect what they wish they had. Motivations ("Why is this chosen or preferred?") suits surveys that ask why customers buy or stay. The list is grouped into Drivers, Issues, Actors, Context and Comparisons, and the Dimensions you choose appear under My List. See Add Dimensions to a Report, What is the Pain Points Dimension? and What is the Unmet Needs Dimension?.
Every Dimension multiplies the queries of every row. A survey of 1,200 answers analyzed with the Automatic Classifier, the Sentiment Classifier, Pain Points and Unmet Needs uses 1,200 × 2 × 2 = 4,800 queries. You can start with fewer Dimensions and add others later from the Report's Dimensions page. See How to Calculate Queries.
Queries = rows × models × Dimensions. Only answers with text are counted, and the Review step shows the Required Query before anything starts.
Review and Create
The Review step shows your choices before anything is analyzed. The Report Title is optional, and a title that names the survey and its wave, such as "Customer Survey Q3", makes the Report easy to find later. Choose the Report Language: English, Spanish, French, German, Portuguese, Dutch or Turkish. It is the language Kimola writes theme names, Dimension answers and summaries in. The answers can be in any of the 30+ languages Kimola analyzes, whatever the Report Language, so a survey answered in several languages gives one Report. See Language Options in Reports.
Check Dataset and Required Query, then click Create Report. If your package doesn't have enough queries left for every answer, the step says so before you continue, and only part of the file is analyzed if you proceed. When the analysis is complete, Kimola shows Here we go! and the Report is ready in your Reports list.
Step 4: Read the Results
A Report is read from the whole to the detail. Overview gives the whole picture, Performance ranks the themes, and Dimensions and Content show the answers behind the numbers.
Start with Overview
The Overview is the first page of the Report. TOTAL DATA shows how many answers Kimola analyzed, and SENTIMENT shows the share of positive, negative and none. BEST PERFORMING THEMES and WORST PERFORMING THEMES list the three themes respondents are most and least satisfied with. A card for every Dimension shows its most frequent answers, and the EXECUTIVE SUMMARY writes up what the whole survey says, followed by a summary of every large theme. The SIGNALS card at the top shows the strongest Signals, when the Report has any.
[Screenshot: The Overview of a survey Report with the TOTAL DATA, SENTIMENT, BEST PERFORMING THEMES and WORST PERFORMING THEMES cards]
Rank the Themes in Performance
Performance gives every theme a Satisfaction Score and a Dissatisfaction Score from 0 to 100: its share of positive or negative answers, statistically adjusted so that a theme with a handful of answers and a theme with hundreds can be compared fairly. Read the worst performing themes first. They are the themes that cost you the most satisfaction, and the first place to look when you decide what to fix.
Read the Answers in Dimensions
The Dimensions page shows, for each Dimension you added, how many answers address it, an AI-written summary of what those answers say, and the answers grouped as clusters with their record counts, their shares and quotations in respondents' own words. Open Pain Points to see what respondents complain about and Unmet Needs to see what they ask for. One answer can give several answers to the same Dimension, so the shares of its clusters can add up to more than 100%.
For the customer survey of a mobile network, the Pain Points summary might say that respondents struggle most with weak coverage in rural areas and with bills they can't read. The Unmet Needs summary might say that they ask for a clearer view of their data usage.
[Screenshot: The Dimensions page open on Pain Points, with the summary and the clusters]
Check the Verbatims in Content
Numbers tell you how much, and the answers tell you why. Content lists every answer with its column values, its Dimension answers, its sentiment and its themes. Pick a theme or a Dimension answer from the filters, or click a word in Most frequent words, to read only the answers behind it. The search box finds answers by the words they contain, and an asterisk at the end of a word finds every word that starts with it, so refund* finds refund, refunds and refunded. Reading a few answers of a theme is the quickest way to see whether its label fits what respondents wrote. See Filter Records in Reports for every filter.
Step 5: Break Down by Respondent Groups
The columns you kept in the file turn the Report into a comparison between groups: one customer segment against another, one region, one product, one score band or one survey wave. Four pages answer this, each for a different kind of question.
Compare Groups Side by Side
Compare sets up to 5 groups side by side. With Compare by Columns, choose a column and the values you want, such as two regions or the lowest and the highest rating. With Compare by Filters, choose saved filters instead; see Save Filters in a Report. Every group gets the same measures: its volume, its trend over time, its sentiment, its themes, its Dimension answers and its popular terms. A theme that one group has and the first group doesn't is listed under Mismatches, which is often the most telling result. Compare reads the analysis the Report already has, so it uses no queries.
[Screenshot: The Compare page with two values of a column side by side]
Cross Themes with Columns in Tables
Tables is where you cross-tab the answers. Drag a column, a classifier or a Dimension into the table, and Kimola groups the answers by it, with the count, the share and the sentiment of each group. Drag a second one to split every group again. A table grouped by Region and then by Pain Points shows the pain points of each region. A column of numbers, such as a score, can be measured instead of grouped, with Average, Sum, Minimum, Maximum or Median for every group. Save a table to reopen it later, or pin it to the Overview.
A software company's survey file has a Plan column and a 0–10 Score column. Group the table by the themes of the Automatic Classifier and measure Score with Average. Each theme then shows the average score of its answers, and the average of all answers is shown beside them.
Score the Themes for One Group
Performance takes the same column filters. Pick a value from Columns, such as one region or one plan, and both lists of themes are calculated again for the answers of that group only. This shows which themes satisfy or upset one group, and not only the whole survey.
Let Signals Point to Differences
Signals are statistically tested findings. A Difference says that a topic is mentioned more, or more negatively, in one group than in the others, where a group is a value of one of your columns or an answer of a Dimension. A Trend says that the mentions of a topic changed over time, and it needs the dates of the answers. Kimola generates a Report's Signals after the analysis. Click Open in Tables on a card to see the records behind it. See What is a Signal?.
A Report with too few answers or too few descriptive columns may have no Signals. More answers, and columns such as product, region or plan, give the tests more to compare.
What You Get
The Report gives you the following from the answers themselves.
Themes with sentiment. Every answer is grouped under the themes it mentions and labeled positive, negative or none, with each theme's share of the survey.
Scores. A Satisfaction Score and a Dissatisfaction Score for every theme, and the best and worst performing themes of the whole survey or of one group.
Pain Points and Unmet Needs. The answers grouped as clusters, with record counts, an AI-written summary and quotations in respondents' own words.
Group breakdowns. The same measures for each respondent group in Compare, a table of themes crossed with any column in Tables, and Performance scores for one group.
Signals. The statistically tested differences between groups and changes over time, when the Report has enough data.
Exports. The Export menu of the Overview offers Excel, CSV, PDF, PowerPoint and Email, and every summary card can be copied or downloaded as an image.
Next Steps
To turn the findings into work, open Actions in the menu of the Report. Kimola writes up to 12 evidence-checked actions for a Profile, each with a confidence level, an owner and a metric. Action Plans written from a Report are available in every package. See Create an Action Plan.
If your survey includes a 0–10 recommendation question with a comment, see How to Analyze NPS Survey Comments. To analyze answers that arrive later, create a new Report from the new file or from the same spreadsheet. A survey that repeats every month or quarter can also be followed file by file in a Space, which is available in the Enterprise package; see What is a Space?. For more on what Kimola does with survey data, see Survey Analysis.