A fastText-based hybrid recommender

Facebook Research’s new fastText library can learn the meaning of metadata from the text it labels. By labelling documents with the users who read them, we used fastText to hack together a “hybrid recommender” system, able to recommend documents to users using both collaborative information (“people who read this also liked that”) and whether the text in the documents is thematically similar to things they read previously. Early signs are it performs quite well, so we’ll continue to experiment with it.

Give me five

Give me five is an open source Chrome extension that allows you to recommend the content you push to Lateral based on the content of the page you’re currently visiting. It’s the same code base that the NewsBot Chrome extension is built upon. The screencast shows the extension in action: You can find the source code […]