What it does
BERTopic is a Python library for topic modelling: it reads a large set of documents and groups them by what they are about, then labels each group with its most telling words.
It uses AI language models to understand meaning, so it can group texts that use different words for the same idea. It supports many variations, including topics that change over time, guided topics and topics in images, and it can use large language models to write topic labels.
Who it's for
Researchers, data analysts and developers who need to make sense of large amounts of text.
Can I use it without coding?
Developers only. It's a Python library, though free online notebooks let you try it with little setup. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- BERTopic paperResearch paper · Mar 2022