Skip to main content

TOPICS

The TOPICS commands lets you predict the topics of a piece of text given a text column as input. Only the text column specified will be analysed and for each entry a topic will be associated.

The command will append two columns to the output: topic_id and topic_name.

NOTE: TOPICS currently works only for English. You can use our TRANSLATE function to convert from 120 different languages into English.

Syntax

TOPICS(<column_name> [, min_topic_size=<min_topic_size>])
  • column_name the input column name to run the topic analysis on. This must be a text column.

Options

  • min_topic_size can be used to specify columns the minimum size of a topic.

Returns

Appends two new columns to the input data set: topic_id and topic_name. Similar to clustering, topic_id holds an integer value describing what group the row is associated with. The topic_name field holds the name of the group - ie the topic - as a text value.

Examples

Predicts the topics of the text in the column Review Text.

SELECT * FROM reviews TOPICS("Review Text");