Mirrors
/
the-algorithm
mirror of https://github.com/twitter/the-algorithm.git
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
the-algorithm/src/scala/com/twitter/recos/user_video_graph
History
twitter-team ef4c5eb65e Twitter Recommendation Algorithm 
Please note we have force-pushed a new initial commit in order to remove some publicly-available Twitter user information. Note that this process may be required in the future.
 		2023-03-31 17:36:31 -05:00
..
relatedTweetHandlers Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
store Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
util Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
BUILD Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
LoggingUserVideoGraph.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
Main.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
README.md Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
UserVideoEdgeTypeMask.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
UserVideoGraph.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
UserVideoGraphConfig.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
UserVideoGraphEdgeHttpHandler.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00
UserVideoGraphWriter.scala Twitter Recommendation Algorithm 2023-03-31 17:36:31 -05:00

README.md

UserVideoGraph (UVG)

What is it

User Video Graph (UVG) is a Finalge thrift service built on the GraphJet framework. In maintains a graph of user-video engagements and serves user recommendations based on traversals in this graph.

How is it used on Twitter

UVG generates video recommendations from a given seed tweet set. It recommends tweets based on collaborative filtering & random walks.

UVG is a stateful service and relies on a Kafka stream to ingest & persist states. The Kafka stream is processed and generated by Recos-Injector. It maintains an in-memory user engagements over the past 24-48 hours. Older events are dropped and GC'ed.

For full details on storage & processing, please check out our open-sourced project GraphJet, a general-purpose high performance in-memory storage engine.