About Insights mention classification

Insights analyzes all the data it collects to give you richer information about your search results. Insights classifies each mention by sentiment, emotion, location, and gender (where possible). You get a deeper understanding of who is talking about your topic, and how they feel about it.

Sentiment

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

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

Emotion

Insights classifies mentions based on six emotions: anger, disgust, fear, joy, surprise, and sadness. If Insights doesn't detect an emotion, it does not assign any emotion to the mention.

Emotion analysis uses an AI-driven model based on a training sample of approximately two million posts, manually labeled with categories of emotion.

Location

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.

Gender

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