News and media content analysis

Code news articles by frame and tone for a media study.

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
`headline`	Article headline
`outlet`	Publication
`date`	Publication date
`text`	First paragraphs of the article

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
`frame`Pick one	Which frame does the article mainly use?	economic Money, jobs, prices, markets health Health effects or risks conflict Disagreement between people, parties or groups human interest The story of one person or family policy Laws, rules or government action
`tone`Scale	How does the article portray its subject?	negative neutral positive Lowest to highest
`cites_study`Yes or no	Does the article cite a study, survey or official statistic?	yes It cites a study, survey or official statistic no It cites none

Example row

Column	Value
`headline`	Tariffs put small importers on the brink
`outlet`	Regional Daily
`date`	2026-04-02
`text`	Importers of European wine say new tariffs could double their costs by summer. One Denver shop owner said she has already cut her order in half...

Answers from a test run on this row

Column	Answer	Confidence
`frame`	economic	94%
`tone`	negative	98%
`cites_study`	no	93%

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`
App store reviews	Sort app reviews into bugs, requests and praise, and see which version the problems come from.	`category` `sentiment` `crash`
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`