Topic modeling helps you discovertopics(call drivers) in conversations between contact center agents and end users. These conversations can be either phone call transcripts or chat logs. You can use this information to improve the quality, speed, and coverage of your contact center dispositioning. Some use
cases include:
Monitoring topic trends to keep your agents updated.
Supporting agent training as new topics are observed.
Using topics and their distribution to help define Dialogflow intents.
The topic modeling workflow follows these steps:
Create a topic model from a set of conversations.
The model generates a list of topics that describes the call drivers.
Curate the topic list according to your preference and business need.
Deploy the model to classify incoming conversations.
Create new versions of your topic model through import and export.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-11-11 UTC."],[],[]]