Skip to main content

  Article updated: October 22, 2021

Mention classification in Insights

Insights runs additional analysis on each mention so that you have richer data about the online conversations you care about.

Insights uses custom-built statistical classifiers that predict sentiment and emotion based on a training set of millions of pieces of data. Insights also infers gender and location for each mention, where possible.


Insights performs sentiment analysis on every mention, using an AI-driven model based on a training sample of 500,000 mentions. Insights assigns a sentiment of positive, negative, or neutral to each mention.

Team admins can change the sentiment assigned to a mention. See Analyze and filter your Insights search results for more information.


Insights performs emotion analysis on every mention, using an AI-driven model based on a training sample of approximately two million tweets, manually labeled with emotional categories.

Insights classifies mentions based on six emotions: anger, disgust, fear, joy, surprise, and sadness. If Insights doesn't detect an emotion, no emotion is assigned to the mention.

Note: Insights only supports emotion classification for English mentions.


Location data is sometimes provided by the platform or by the author of the mention. When an author or mention has no explicit location, Insights tries to infer a location based on keywords in the author’s bio.


Insights infers gender for a mention using a statistical method based on the binary gender distribution of author names in census data and other public records.

Supported languages

Insights detects and returns mentions data in the following languages. Languages marked with an asterisk (*) are not supported for sentiment analysis. Insights only supports emotion analysis for English mentions.

Supported languages for mention classification
Supported languages