Twitter Open Sources Most of Its Algorithms: What That Means

Twitter has finally made most of its recommendation algorithm open source, which is now available to independent third parties and users.

According to Twitter CEO Elon Musk, many embarrassing issues are being exposed, but “we’re fixing them quickly.”

“The acid test is that independent third parties should be able to determine with reasonable accuracy what is likely to be shown to users,” Musk wrote on Saturday.

Musk said that most of the recommendation algorithms will be made open source and the rest will follow.

According to Twitter, “the referral pipeline consists of three main steps.”

“Fetch the best tweets from various recommendation sources in a process called candidate sourcing; Classify each tweet using a machine learning model; and apply heuristics and filters, such as filtering out tweets from users you’ve blocked, NSFW content, and tweets you’ve already seen,” the microblogging platform explained.

The service responsible for building and serving the For You timeline is called Home Mixer.

“Home Mixer is based on Product Mixer, a custom Scala framework that makes it easy to build content feeds. This service acts as a software backbone that connects different candidate sources, scoring functions, heuristics and filters,” the company elaborated.

The goal of the For You timeline is to provide people with relevant tweets.

Twitter has several candidate sources that it uses to retrieve the most recent and relevant tweets for a user.

“At this point, we have 1,500 candidates in the pipeline that may be relevant. The score directly predicts the importance of each candidate tweet and is the primary signal for tweet placement in the timeline,” the company said.

At this stage, all candidates are treated equally, regardless of the candidate source.

“Our recommendation system consists of many interconnected services and jobs. There are many areas in the app where tweets are recommended – Search, Explore, Ads,” the company said.

Read all the Latest Tech News here.