MaartenGr/BERTopic

Health v2 · maintenance only

Adoption not part of the score

7902 stars · 930 forks observed · 2026-10-21

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

BERTopic is a Python library for topic modeling that leverages transformer-based sentence embeddings and class-based TF-IDF (c-TF-IDF) to discover easily interpretable topics in document collections. It supports guided, supervised, hierarchical, dynamic, online, multimodal, zero-shot, and LLM-enhanced topic modeling variants.

Use cases

• discover topics in a corpus of documents
• cluster customer reviews into themes
• track how topics evolve over time
• visualize topics like pyLDAvis
• do zero-shot topic modeling with seed keywords
• summarize topic descriptions with LLMs
• model topics from images
• incrementally model topics in a stream of documents

When to choose

• you need interpretable topics from text using modern transformer embeddings
• you want flexible topic modeling modes (supervised, dynamic, hierarchical, online)
• you are working in Python and want an actively maintained, well-documented topic modeling library

When to avoid

• you need a lightweight classic LDA implementation without transformer dependencies
• you work outside Python or need a hosted no-code service
• your corpus is tiny and embedding models would be overkill

Facets

library · maturity stable

nlp machine-learning data-science data-visualization machine-learning data-science python cross-platform topic-modeling bert transformers sentence-embeddings ctfidf clustering unsupervised-learning natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MaartenGr/BERTopic")