Twitter's Recommendation Algorithm: Source Code for Building Feeds of Content

The Twitter Recommendation Algorithm is an open-source set of services and jobs responsible for constructing and serving the Home Timeline. It includes different models for community detection, knowledge graph embeddings, detecting NSFW or abusive content, predicting the likelihood of a user interacting with another user, calculating user reputation, and providing recommendations for accounts to follow and Tweets from those accounts. The algorithm uses a combination of machine learning models and human curation to filter and rank Twitter content. The source code is available on Github under the AGPL-3.0 license and contributions from the community are welcome.