BERTopic is a Python package for topic modeling that uses transformer-based embeddings and class-based TF-IDF to create dense document clusters with interpretable topic descriptions.
It’s designed for extracting themes from collections of text documents, while offering flexible configuration for embeddings, dimensionality reduction, clustering, tokenization, topic weighting, and representation models.
This is free and open source software.
Key Features
- Supports guided, supervised, semi-supervised, manual, hierarchical, dynamic, online, multimodal, zero-shot, and class-based topic modeling.
- Provides methods to fit models, transform new documents, inspect topics, retrieve representative documents, merge topics, reduce topics, and reduce outliers.
- Includes visualization tools for topics, documents, hierarchies, heatmaps, term scores, topic distributions, and topics over time.
- Offers modular components for embeddings, dimensionality reduction, clustering, vectorization, weighting, and topic representation.
- Supports custom topic representations, including KeyBERT-inspired representations and LLM-based labels or summaries.
- Can be installed with optional backends for Flair, Gensim, spaCy, TensorFlow USE, fastembed, and vision-based workflows.
Website: github.com/MaartenGr/BERTopic
Support:
Developer: Maarten P. Grootendorst
License: MIT License
BERTopic is written in Python. Learn Python with our recommended free books and free tutorials.
Related Software
| Python Natural Language Processing Tools | |
|---|---|
| PyTorch-Transformers | Library of state-of-the-art pre-trained models for NLP |
| NLTK | Natural Language Toolkit |
| spaCy | Industrial strength natural language processing |
| scikit-learn | Machine learning library |
| Gensim | Vector space modeling and topic modeling toolkit |
| flair | Simple framework for state-of-the-art NLP |
| TextBlob | Python (2 and 3) library for processing textual data |
| textacy | Python library for performing NLP tasks |
| polyglot | Multilingual text (NLP) processing toolkit |
| AllenNLP | Apache 2.0 NLP research library |
| Snips NLU | Natural Language Understanding Python library |
| PyNLPI | Various modules useful for common, and less common, NLP tasks |
| nlpnet | Natural Language Processing with neural networks |
| Pattern | Web mining module |
| GluonNLP | Deep Learning for NLP |
| PyTorch-NLP | Neural network layers, text processing modules and datasets |
| NLP Architect | Deep Learning NLP/NLU library |
Read our verdict in the software roundup.
 Explore our comprehensive directory of recommended free and open source software. Our carefully curated collection spans every major software category.This directory is part of our ongoing series of informative articles for Linux enthusiasts. It features hundreds of detailed reviews, along with open source alternatives to proprietary solutions from major corporations such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk. You’ll also find interesting projects to try, hardware coverage, free programming books and tutorials, and much more. Discovered a useful open source Linux program that we haven’t covered yet? Let us know by completing this form. |