Survey response coder
Code open-ended survey answers into themes and sentiment, thousands at a time.
Turns free-text answers into data: each response is tagged with every theme it mentions (a response can have several), a sentiment, and whether it suggests a specific change. Edit the themes to match your codebook, then run your whole export as a batch.
Try it live
Real calls to Jev. Pick an example or paste your own.
Pick an example or paste your own input, then run it.
Under the hood
Every question and rule, in the open. Fork it to change any of them.
What it asks
Reads question and response, then asks 8 questions in one call.
- Q1Theme: priceYes / no
Does the
responsetalk about price, cost or value for money? - Q2Theme: ease of useYes / no
Does the
responsetalk about how easy or hard the product is to use? - Q3Theme: featuresYes / no
Does the
responseask for or discuss specific features? - Q4Theme: supportYes / no
Does the
responsetalk about customer support or service? - Q5Theme: speed & reliabilityYes / no
Does the
responsetalk about speed, bugs, outages or reliability? - Q6Theme: getting startedYes / no
Does the
responsetalk about setup, onboarding or learning the product? - Q7SentimentPick one
What is the overall sentiment of the
response?PositiveNegativeMixedNeutral - Q8Suggests a changeYes / no
Does the
responsesuggest a specific change the team could make?
How it decides
Rules run in code, top to bottom. The first one that matches gives the verdict.
- 1Otherwisethe answer to “Sentiment”
- ·DefaultNeutral
Call it from your code
Every template runs as-is with an API key, no setup: POST /api/v1/judges/survey-coder/run.
curl -X POST https://tryevally.com/api/v1/judges/survey-coder/run \ -H "Authorization: Bearer $EVALLY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": { "question": "What'\''s one thing we could do better?", "response": "The app is great once you get going, but setup took me two days and support took 48 hours to reply. For $49 a month I expected faster help." }}'Seen in the wild
Community builds on Jev that use this pattern. Not affiliated with Evally.
More in Research & data
- Research & data
Systematic review screener
Screen abstracts against your inclusion and exclusion criteria, one criterion at a time.
IncludeFull-text reviewExclude5 questions - Research & data
Sentiment & emotion
Sentiment, the dominant emotion, its intensity, and whether it's sarcastic.
Very negativeNegativeNeutral+24 questions - Research & data
Record matcher (dedupe)
Do these two records describe the same person, company or product?
MatchPossible matchDifferent4 questions - Research & data
News & event severity
Rate headlines by severity, topic and region, and alert on the ones that matter.
AlertWatchLog4 questions - Research & data
Research desk router
Send each item in a research feed to the right desk: papers, repos or market news.
No deskPapers deskRepos desk+11 questions - Research & data
Novelty check: new, update or duplicate?
Check a fresh note against what you already know: new, an update, or a duplicate.
NewUpdateDuplicate1 questions