Topic Categorisation

Topics allow you to assign labels to ingested transcripts based on various types of logic.

Groups of labelled transcripts can be used to identify how people are using your application and specifically why users are engaging with your product. It is then possible to look at success metrics such as user feedback ratings or user input sentiment per-topic, to understand which types of interaction are leaving your users satisfied, and where they're dissatisfied.

There are currently 3 types of logic that can be used to assign a topic to a transcript:

  1. Semantic Topic - Semantic topics use semantic matching to apply a topic label based on a semantic match between a label and a message. This is the most commonly used topic type, and allows for matching of topics that have a semantic meaning. Multiple semantic match labels can be assigned to a specific topic, and these match using OR logic, rather than AND.

  2. Intent Topic - Intent topics use an LLM to match on the intent of the user, using an LLM. This topic type accepts both an intent and also an optional set of positive and negative examples. This is a premium feature that is enabled for paid accounts.

  3. Keyword Topic - Keyword topics use exact keyword matching to match against a provided string.

Last updated