the-algorithm/README.md at main · twitter/the-algorithm

Source code for Twitter's Recommendation Algorithm - the-algorithm/README.md at main · twitter/the-algorithm

SimClusters: Community-based Representations for Heterogeneous Recommendations at Twitter Overview SimClusters is as a general-purpose representation layer based on overlapping communities into which users as well as heterogeneous content can be captured as sparse, interpretable vectors to support a multitude of recommendation tasks. We build our user and tweet SimClusters embeddings based on the inferred communities, and the representations power our personalized tweet recommendation via our online serving service SimClusters ANN. For more details, please read our paper that was…

saved by

• Adithya V
• Neil Warren

related reading

• GitHub - igorbrigadir/awesome-twitter-algo: The release of the Twitter algorithm, annotated for recsys · GitHubgithub.com
• GitHub - eleurent/twitter-graph: Fetch and visualize the graph of your Twitter friends and followers.github.com
• Remains of the Dayeugenewei.com
• What do I think about Community Notes?vitalik.eth.limo
• How to Blow Up a Timeline - Remains of the Dayeugenewei.com
• The Serendipity Machine (Notes on Using Twitter) — Nabeel S. Qureshinabeelqu.co
• How to Twitter Successfully | near.blognear.blog
• Seeing Like an Algorithm - Remains of the Dayeugenewei.com
• Threads and the Social/Communications Map – Stratechery by Ben Thompsonstratechery.com
• how to optimise twitter for good ML research takes (or anything else)space.ong.ac
• GitHub - ansonyuu/matchmaking: Embedding space of names clustered based on their interests using the sentence-transformers all-MiniLM-L6-v2 modelgithub.com
• Vector embeddings | OpenAI APIdevelopers.openai.com