Research

Classify Survey Responses with AI

Product, Pricing, Support Experience, Onboarding, Documentation — multi-label topic classification for open-ended survey answers.

Open in Data Classification Prompt

Overview

Open-ended survey questions produce the most valuable and least countable feedback: one answer touches pricing, onboarding, and the docs in three sentences. This setup classifies responses by topic in Multiple Labels mode — every topic that's genuinely addressed, strongest first — with definitions that keep adjacent topics apart: Support Experience is about interactions with the team, Documentation is about the help content itself, Onboarding is the getting-started phase regardless of what it touched. Conservative ambiguity keeps topic counts honest.

How to use this resource

Classify per response

Each answer gets its own label list — aggregation into counts happens in your sheet, with traceability per response.
Respect the mention threshold

"A merely mentioned topic does not earn its label" — a pricing aside in an onboarding story should not count as pricing feedback.
Keep waves comparable

Freeze the label set and definitions across survey waves — changed definitions mean uncomparable counts.

Why This Works

Multi-label matches the bundled nature of open-ended answers
Team-vs-content definitions cleanly split support and documentation feedback
Conservative policy keeps trend lines driven by real signal, not generous labeling

Best for

Research teams with hundreds of free-text responses per wave
Surveys whose answers bundle multiple topics
Topic taxonomies with adjacent, easily-confused categories

Not for

Extracting the quotes worth keeping — pair with the Extraction Prompt Generator for that
Sentiment per topic — run sentiment as its own classification pass

Use cases

Making open-ended answers countable by topic
Tracking topic mix across survey waves
Splitting support-experience feedback from documentation feedback

FAQ

How does this keep Support Experience and Documentation feedback from being confused?

With definitions that draw the line, not just label names. Support Experience is defined as feedback about interactions with the support team, while Documentation is about guides, help articles, or missing documentation — the content itself. CLASSIFICATION RULES require matching text against the definitions, not the names, so a complaint about the help article lands as Documentation even if support is mentioned nearby.

Can one survey answer get more than one topic label?

Yes — this runs in Multiple Labels mode. The EDGE CASE RULES return every label that applies and order them by how strongly each applies, strongest first, which fits open-ended answers that bundle pricing, onboarding, and docs in one response. Output is a single JSON object with a "labels" array using the label text exactly as defined.

Why won't a topic that's only mentioned in passing get counted?

A deliberate honesty threshold sits in the EDGE CASE RULES: "A merely mentioned topic does not earn its label — it must be a real subject of the text." A pricing aside inside an onboarding story doesn't count as pricing feedback. Combined with the conservative AMBIGUITY POLICY, it keeps topic counts driven by real signal so trend lines across waves stay meaningful.

Customize This Resource

Opens this setup in Data Classification Prompt. Generate to get the full classification prompt — then adjust the labels, ambiguity mode, and confidence output.

Open in Data Classification Prompt

Prompt Template

Copy it as-is, or use Open in Data Classification Prompt to load it pre-filled and customize it with your own context.

TASK
Categorize open-ended survey responses by the topics they address.
Assign one or more of the labels defined below to the text in the input.

LABELS
- Product: Feedback about the product itself — features, quality, reliability.
- Pricing: Feedback about cost, plans, or perceived value for money.
- Support Experience: Feedback about interactions with the support team.
- Onboarding: Feedback about getting started — setup, first use, learning curve.
- Documentation: Feedback about guides, help articles, or missing documentation.

CLASSIFICATION RULES
- Read the entire text before deciding — the deciding signal may come late.
- Judge by content and intent, not by tone, length, or formatting.
- Match the text against the definitions, not just the label names.
- Use only the labels defined above — never invent a new label.

EDGE CASE RULES
- If the text fits more than one label, return every label that applies.
- Order the labels by how strongly each applies, strongest first.
- A merely mentioned topic does not earn its label — it must be a real subject of the text.

AMBIGUITY POLICY
- Choose a label only when its definition genuinely covers the text.
- When torn between two labels, re-read both definitions and pick the closer one — do not guess from the names.

OUTPUT FORMAT
Return your classification as a single valid JSON object with a "labels" array.

EXAMPLE OF A VALID RESPONSE
{
  "labels": ["Product", "Pricing"]
}

OUTPUT RULES
- Return only the JSON object — no text before or after it.
- Do not wrap the output in markdown code fences.
- Return the label text exactly as defined above — no paraphrasing, no abbreviations, no new labels.

More resources from Data Classification Prompt

Resource

Classify Support Tickets with AI

Billing, Technical, Account, How-To, Feature Request — ticket triage with definitions that decide the borderline cases for the model.

Support

Resource

Text Classification Prompt — the Anatomy

The blocks a reliable classification prompt needs: defined labels, classification rules, edge-case rules, an ambiguity policy, and a confidence contract.

Prompt Engineering

Resource

Categorize Customer Feedback with AI

Praise, Complaint, Feature Request, Bug Report, Question — multi-label feedback categorization where one message can carry three signals.

Product

Resources that pair well

Resource

Extract Data From Text with AI

Free text in, named fields out. The extraction prompt pattern that turns any unstructured text into consistent, parseable records.

Prompt Engineering

Resource

Force JSON Output from AI

Stop getting 'Sure, here is the JSON…' — the output-contract pattern that forces models to return only parseable JSON: schema, example, and a strict rule block.

Prompt Engineering

Resource

Fix Invalid JSON from AI

The JSON won't parse and you can't see why. Deterministic cause-sniffing — trailing commas, single quotes, unclosed brackets — and the repair prompt that fixes it.

Engineering

Related tools

Tool

Data Classification Prompt

Build classification prompts that assign labels from a closed set — with label definitions and edge-case rules.

Structured Output

Tip: Save time by exploring related resources and tools that integrate with this resource.