Map Free-Text Feedback into Themes with AI: Handle Multiple Labels and Unclassified Responses
This exercise classifies six short free-text comments into predefined themes and allows multiple labels when one response contains more than one topic. It also explains why the total number of labels can exceed the number of respondents and how to avoid unsupported conclusions about satisfaction or emotional intensity.
Content checked 2026.09.23Copyable prompts
Show contents
Who this is forBeginners who want to organize short survey or review comments by theme but are unsure how much they can trust the counts and interpretation
What you need
You only need to be able to separate short comments into individual lines.
All F1–F6 responses in this exercise are fictional.
You do not need to enter personal data from real customers, employees, or participants.
01Prepare the six comments exactly as written with IDs
When classifying free-text feedback, first preserve each sentence as written instead of summarizing it immediately. A single short response can contain two different themes. In this example, F3 mentions both text size and insufficient location signage, so choosing only one would lose information. F6, which says no comment, should not be forced into a positive or negative category.
Sample input
F1 The information text is too small
F2 The location guidance is difficult to follow
F3 The information text is too small and there are not enough location signs
F4 The facilitator's explanation is friendly
F5 I would like to participate again
F6 No comment
The labels used in this exercise are visual guidance, location guidance, facilitator, repeat participation, and hold for classification. Emotional scores or satisfaction levels are not present in the source, so they should not be created.
Response ID
Key expression
Possible number of labels
F1
Information text is too small
1
F2
Location guidance is difficult
1
F3
Information text is too small and location signs are insufficient
2
F4
Facilitator's explanation is friendly
1
F5
Would like to participate again
1
F6
No comment
1
02State the rules for multiple labels and hold for classification
When asking AI to classify themes, define not only the label names but also whether multiple labels are allowed. If one person's response can cover several themes, the total number of labels does not have to equal the number of respondents. In this example, the target counts are visual guidance 2, location guidance 2, facilitator 1, repeat participation 1, and hold for classification 1, for a total of 7 labels.
Prompt
Classify comments F1–F6 using the 5 labels below.
Labels:
- Visual guidance
- Location guidance
- Facilitator
- Repeat participation
- Hold for classification
Rules:
- Allow multiple labels when one comment clearly contains different themes.
- If two themes are explicitly present, as in F3, assign both labels.
- If a response has no evaluative content, such as no comment, assign hold for classification.
- Do not infer positive or negative emotional intensity, satisfaction scores, or whether all participants were satisfied.
- Do not add reasons that are not in the original comment.
- Preserve each response ID and original text.
- At the end, count the number of responses assigned to each label.
If the instruction allowing multiple labels is omitted, F3 may be forced into only one category. Allowing a hold category in advance also reduces the temptation to force an empty response into an unrelated theme.
03Check individual labels and totals together
The result below is not a measurement of the classification accuracy of any particular AI system. It is an editorial example created and reviewed with AI assistance to show how the input connects to label counts. A person should read F1–F6 one by one and verify the assigned labels.
Example result
F1 → Visual guidance
F2 → Location guidance
F3 → Visual guidance, Location guidance
F4 → Facilitator
F5 → Repeat participation
F6 → Hold for classification
Label counts:
Visual guidance 2
Location guidance 2
Facilitator 1
Repeat participation 1
Hold for classification 1
Number of respondents: 6
Total labels: 7
Because F3 has multiple labels, a total of 7 labels being greater than 6 respondents is not an error.
ID
Original comment
Label
Contribution to count
F1
The information text is too small
Visual guidance
Visual guidance +1
F2
The location guidance is difficult to follow
Location guidance
Location guidance +1
F3
The information text is too small and there are not enough location signs
Visual guidance, Location guidance
Visual guidance +1, Location guidance +1
F4
The facilitator's explanation is friendly
Facilitator
Facilitator +1
F5
I would like to participate again
Repeat participation
Repeat participation +1
F6
No comment
Hold for classification
Hold for classification +1
04Do not expand theme classification into unsupported satisfaction analysis
A theme map organizes what topics were mentioned. It does not automatically determine participants' emotions or overall satisfaction. F4 says the facilitator was friendly and F5 says the respondent would like to participate again, but that does not support a claim that all 6 respondents were satisfied. The complaints in F1–F3 also do not provide a basis for assigning an intensity score.
Flawed result
Overall participant satisfaction was very high. All 6 participants were positive about the event, and F1–F3 only expressed mild dissatisfaction. F6 had no particular complaints, so that respondent can also be considered satisfied.
Unsupported inference
Why it is a problem
What to record instead
All 6 were positive
F1–F3 and F6 do not provide evidence for overall satisfaction
Record only the theme labels for each response
Mild dissatisfaction
Emotional intensity is not stated in the source
Record only the content about text size or location guidance
F6 was satisfied
No comment does not mean satisfied
Hold for classification
To reduce this type of error, treat themes, emotions, satisfaction, and behavioral intention as different analysis dimensions. This exercise classifies only themes. F5's statement about participating again is recorded only as repeat participation.
05Correct missing labels or unsupported interpretation with a targeted re-request
If F3 is classified only as location guidance or F6 is classified as positive, you can specify those IDs and ask for a correction. Providing expected totals as a check value also makes it easier for a person to verify the revised result.
Prompt
Review the classification result again.
- F3 contains both information text is too small and location signs are insufficient, so assign both Visual guidance and Location guidance.
- F6 says no comment and contains no evaluative content, so assign Hold for classification.
- Do not infer emotional intensity or satisfaction.
After correction, check whether the counts match the following:
Visual guidance 2
Location guidance 2
Facilitator 1
Repeat participation 1
Hold for classification 1
There are 6 respondents, but because multiple labels are allowed, the total number of labels is 7. Do not treat this difference as an error.
Providing expected totals does not mean classifications should be forced to match the numbers. The totals are check values that should be recalculated from the source. The final decision should come from verifying whether each response matches the label definition.
06Final check: keep respondent count and label count separate
With multiple labels, it is normal for the number of people and the number of labels to differ. When reporting results, do not treat 6 respondents and 7 labels as the same type of count. Use the checklist below to verify both the individual assignments and the totals.
Checklist
[ ] Is F1 labeled Visual guidance?
[ ] Is F2 labeled Location guidance?
[ ] Does F3 have both Visual guidance and Location guidance?
[ ] Is F4 labeled Facilitator?
[ ] Is F5 labeled Repeat participation?
[ ] Is F6 labeled Hold for classification?
[ ] Are the counts Visual guidance 2, Location guidance 2, Facilitator 1, Repeat participation 1, Hold for classification 1?
[ ] Are there 6 respondents and 7 total labels?
[ ] Is the total of 7 labels correctly treated as not an error?
[ ] Were unsupported interpretations such as everyone was satisfied or emotional intensity avoided?
With real free-text data, it is useful to test label definitions on a small set of examples before fixing the classification rules. This tutorial is an editorial exercise using 6 fictional comments and does not evaluate the representativeness or statistical significance of survey results.
What to check yourself
Editorial example in which a human recalculated the multiple-label assignments and label totals for the fictional F1–F6 free-text comments
Check that F3 has both Visual guidance and Location guidance
Check that F6 is Hold for classification
Check that the label counts are 2, 2, 1, 1, 1
Check that 6 respondents and 7 total labels are treated as different counts
Check that emotional intensity or universal satisfaction was not inferred
Verification limits
The result is an educational editorial example created and reviewed with AI assistance. It is not the result of analyzing real survey data, measuring classification accuracy, or verifying the automatic classification performance of any specific AI product.
This exercise uses AI to compare V1 and V2 of the same event notice and classify five comparison items as changed, added, deleted, or unchanged. You will learn how to record only differences that actually appear in the documents without assuming why a deleted sentence disappeared.
This exercise turns a short notice into six FAQ entries. Questions supported by the source receive source IDs, while topics such as fees, refunds, and waitlists that do not appear in the notice are left as needs confirmation instead of being answered from assumptions.
This exercise rewrites four fictional borrowing rules in clearer language while preserving the registered-member requirement, the 7-day deadline, the prohibition on extending reserved materials, and the rule that non-reserved materials may be submitted for one extension request without guaranteeing approval.
This exercise shows how to break a vague research goal into factual questions, experience questions, and decision questions, then plan what to verify and where to look. Instead of asking AI to invent search results, you first organize the sources to check and the items that are still unknown.
This exercise shows how to design a 15-minute user interview for improving a fictional application form. You will revise leading questions into neutral questions about recent real behavior and learn not to treat predicted responses as evidence before any interviews have been conducted.
This exercise shows how to define constraints such as participant count, time, printed materials, purchasing limits, and available equipment before asking AI for 4 distinct alternatives. Instead of deciding which idea is best, you check whether each option satisfies the constraints and learn how to revise the request when the constraints change.
This exercise shows how to prepare 6 expected audience questions with source evidence, short answers, and a verification plan when the answer is unknown. It does not cover creating a presentation outline or AI voice evaluation; the focus is on answering questions without overstating limited evidence.