ina-foss/twembeddings

Sentence embeddings for unsupervised event detection in the Twitter stream: study on English and French corpora

47
/ 100
Emerging

This project helps researchers analyze large streams of Twitter data to identify emerging events without predefined categories. It takes a collection of tweets (English or French) as input and groups them into clusters, indicating distinct events. This tool is designed for academic researchers or data scientists who need to detect novel events from social media feeds.

No commits in the last 6 months. Available on PyPI.

Use this if you need to automatically discover new topics or incidents from raw Twitter data for research or analysis.

Not ideal if you're looking for a simple, out-of-the-box application without any programming or command-line interaction.

social-media-research event-detection unsupervised-learning tweet-analysis natural-language-processing
Stale 6m
Maintenance 2 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

33

Forks

5

Language

Jupyter Notebook

License

MIT

Last pushed

Jul 25, 2025

Commits (30d)

0

Dependencies

15

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/ina-foss/twembeddings"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.