App store reviews

Sort app reviews into bugs, requests and praise, and see which version the problems come from.

Run this on your file Download the template CSV

Columns to upload

Name the columns in your CSV like this. Extra columns are fine: every column of the row is sent with the questions.

Column	What it holds
`rating`	Star rating, 1 to 5
`title`	Review title
`review`	Review text
`version`	App version

Questions

Each question adds a column to your file. The answer is one of the listed values, or Unsure when the model's confidence is below the cutoff: 70% for pick-one and scale questions, 80% for yes or no.

New column	Question	Possible answers
`category`Pick one	What is the review mainly about?	bug Something is broken or crashes feature request Asks for something the app does not do performance Slow, drains battery, uses too much data pricing Price, subscription or in-app purchases praise Says what they like, no problem raised
`sentiment`Scale	How does the reviewer feel about the app?	very negative negative neutral positive very positive Lowest to highest
`crash`Yes or no	Does the reviewer say the app crashes, freezes or will not open?	yes They report a crash, freeze or failure to open no They report none

Example row

Column	Value
`rating`	2
`title`	Crashes on checkout
`review`	Since the update it closes every time I tap pay. Liked it before.
`version`	4.2.0

Answers from a test run on this row

Column	Answer	Confidence
`category`	bug	100%
`sentiment`	negative	73%
`crash`	yes	98%

More research use cases

Use case	What it does	New columns
Survey open-ended answers	Code the free-text answers of a survey into themes and sentiment, and pull out the ones that name a specific change.	`theme` `sentiment` `actionable` `off_topic`
User interview snippets	Tag quotes from user interviews by the pain they describe and how serious it is.	`pain_point` `severity` `workaround` `feature_request`
Literature review abstract screening	Screen the titles and abstracts of a literature search against your inclusion criteria before you read the full texts.	`design` `population` `outcome` `include`
News and media content analysis	Code news articles by frame and tone for a media study.	`frame` `tone` `cites_study`
Social listening posts	Code public posts about a topic by stance, and separate first-hand experience from repeated claims.	`on_topic` `stance` `first_hand` `health_claim`