JiaxiWong/MIND-News-RecSys

A Deep Interest Network (DIN) implementation for MIND News Recommendation with BERT semantic warm-up.

35
/ 100
Emerging

This project helps news publishers and content platforms improve how they recommend articles to readers. It takes a reader's past viewing history and the text of new articles as input, then generates a personalized list of recommended news stories. This is designed for product managers or content strategists looking to enhance user engagement and retention on their news platform.

Use this if you need a news recommendation system that can quickly suggest relevant articles, even for brand-new stories or users with limited history.

Not ideal if your primary goal is absolute state-of-the-art overall ranking performance at the expense of computational efficiency or first-hit accuracy.

news-publishing content-personalization user-engagement recommendation-systems digital-media
No License No Package No Dependents
Maintenance 6 / 25
Adoption 7 / 25
Maturity 5 / 25
Community 17 / 25

How are scores calculated?

Stars

36

Forks

10

Language

Jupyter Notebook

License

Last pushed

Dec 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JiaxiWong/MIND-News-RecSys"

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