BERTopic: Neural topic modeling with a class-based TF-IDF procedure

Abstract

Topic models can be useful tools to discover latent topics in collections of documents. Recent studies have shown the feasibility of approach topic modeling as a clustering task. We present BERTopic, a topic model that extends this process by extracting coherent topic representation through the development of a class-based variation of TF-IDF. More specifically, BERTopic generates document embedding with pre-trained transformer-based language models, clusters these embeddings, and finally, generates topic representations with the class-based TF-IDF procedure. BERTopic generates coherent topics and remains competitive across a variety of benchmarks involving classical models and those that follow the more recent clustering approach of topic modeling.

BERTopic has a python implementation, see https://github.com/MaartenGr/BERTopic

Cited by in corpus (4)

• Angler: Helping Machine Translation Practitioners Prioritize Model Improvements
• The Elements of Visual Art Recommendation: Learning Latent Semantic Representations of Paintings
• Weakly-Supervised Scientific Document Classification via Retrieval-Augmented Multi-Stage Training
• Examining European Press Coverage of the Covid-19 No-Vax Movement: An NLP Framework