Twitter has finally open sourced much of its recommendation algorithm which is now available to independent third parties and users. According to Twitter CEO Elon Musk, many embarrassing issues will be discovered, but we will “fix them fast”. The fast test is that independent third parties should be able to determine with reasonable accuracy what users will likely be shown,” Musk posted on Saturday.
Musk said that most of the recommendation algorithms would be made open source and the rest would follow. According to Twitter, “the recommendation pipeline is made up of three main stages”.
“Get the best tweets from a variety of recommendation sources in a process called candidate sourcing; Rank each tweet using machine learning models; and apply heuristics and filters, such as filtering Tweets from users you’ve blocked, NSFW content, and Tweets you’ve seen,” the micro-blogging platform explained.
The service that is responsible for creating and serving the ‘For You’ timeline is called Home Mixer. “The Home Mixer product is built on Mixer, our custom Scala framework that facilitates the creation of content. The service serves as the software backbone that connects the various candidate sources, scoring functions, heuristics, and filters,” The company further elaborated.
For You Timeline aims to serve relevant tweets to people. Twitter has several candidate sources that it uses to retrieve tweets that are recent and relevant to the user. “At this time in the pipeline, we have 1,500 candidates that may be relevant. The scoring directly predicts the relevance of each candidate tweet and is the primary signal for ranking tweets on your timeline,” the company said.
At this stage, all candidates are treated equally, regardless of the source from which the candidate originated.
“Our recommendation system is made up of many interconnected services and jobs. There are many areas of the app where Tweets are recommended – Search, Explore, Ads,” the company said.
The post Twitter Makes Most of Its Recommendation Algorithms Open Source appeared first on Techlusive.