BERTopic and turftopic
These are competitors offering alternative approaches to neural topic modeling: BERTopic uses BERT embeddings with c-TF-IDF for interpretability at scale, while TurfTopic uses sentence-transformers with a focus on robustness and speed, so practitioners typically choose one based on their priorities around interpretability versus performance.
About BERTopic
MaartenGr/BERTopic
Leveraging BERT and c-TF-IDF to create easily interpretable topics.
BERTopic helps you understand the main themes within a large collection of text documents. You provide a dataset of text, like customer reviews, news articles, or research abstracts, and it outputs a list of topics, each defined by a few key words, along with the documents belonging to them. This is ideal for data analysts, researchers, or anyone needing to quickly grasp the core subjects in unstructured text.
About turftopic
x-tabdeveloping/turftopic
Robust and fast topic models with sentence-transformers.
This tool helps you quickly understand the main subjects or themes within large collections of text, like customer feedback, news articles, or research papers. You input a document collection, and it outputs a list of prominent topics, along with key phrases and example documents for each, and even AI-generated topic names. Data analysts, market researchers, and content strategists can use this to make sense of unstructured text.
Scores updated daily from GitHub, PyPI, and npm data. How scores work