How it works: TOPICS

Topic analysis is a technique used to identify and extract common themes or topics from a collection of documents or text data.

TOPICS allows users to perform topic analysis on any kind of text data using Infer's topic modelling algorithm that combines language modelling, dimensionality reduction, and clustering.

In this page, we will look at what exactly happens when you call TOPICS. 🤔

TL;DR:

• TOPICS uses large pre-trained language models to encode the contextual meaning of each piece of text
• UMAP and HDBSCAN (i.e. CLUSTER) are used to group the text into related topics