Twitter follows Elon Musk's promise to make its algorithm "open-source."

Image Credit: Wired Twitter has blogged about the decision and shared the code that determines which tweets appear on your timeline on GitHub. It explains the ranking and filtering criteria used by the algorithm to choose which tweets to display in the For You timeline. The three main stages of Twitter's "recommendation pipeline" are described in the company's blog post. First, it collects "the best Tweets from different recommendation sources," then it ranks those tweets using "a machine learning model," and finally, it filters out tweets from people you've blocked, tweets you've already seen, and tweets that aren't appropriate for work before displaying them on your timeline. Each step of the process is thoroughly explained in the post. For instance, it mentions that the first stage examines over 1,500 tweets and that the intended ratio for the For You timeline is roughly 50 percent tweets from accounts you follow (referred to as "In-Network") and 50 percent tweets from accounts you don't follow (referred to as "Out-of-Network"). Additionally, it states that the ranking is intended to "optimize for positive engagement (e.g., Likes, Retweets, and Replies)" and that the last stage aims to prevent you from seeing an excessive number of tweets from a single user. Image Credit: TWSJ Of course, sifting through the code—which academics are already doing—will yield the most specific information. Elon Musk, the company's CEO, has been promising the change for some time; when he asked his followers on March 24, 2022, whether Twitter's algorithm should be open source, about 83 percent of them responded "yes." In February, he said it would happen within a week, but he later pushed back the deadline to March 31st. Musk stated in a tweet that the "majority of the recommendation algorithm" was revealed on Friday and that the other portions would follow. In a Space discussing the algorithm's release, he said the goal was to make it "the least gameable system on the internet" and as robust as Linux, perhaps the most well-known and successful open-source project. He also said that the hope is "that independent third parties should be able to determine, with reasonable accuracy, what will probably be shown to users." The main objective, he continued, "is to maximize unregretted user minutes." When the algorithm is revealed, Musk has been prepping his audience to be disappointed (which is, of course, making a big assumption that people will understand the complex code). People will "find many foolish things" because it is "overly complex & not fully understood internally," he has said, but he has also vowed to remedy problems as they are found. He tweeted, "Providing code openness will at first be extremely embarrassing, but it should lead to a rapid increase in recommendation quality." There is a distinction between open source code, which allows the public to submit its code for review and apply the algorithm in other projects, and code transparency, which allows users to examine the algorithms that select tweets for their timelines. Musk has stated that it will be open source, but if Twitter wants to claim that title, it must put in the effort. To do that, methods of governance must be developed that determine which pull requests to approve, which user-raised concerns require attention, and how to prevent malicious actors from attempting to destroy the code for their ends. According to Twitter, anyone can submit pull requests that might someday make it into its codebase. Image Credit: TTS The business does claim that it is addressing this. It does, however, go on to say that Twitter's still in the process of building "tools to manage these suggestions and sync changes to our internal repository." But Musk's Twitter has promised to do many things (like polling users before making major decisions) that it hasn't stuck with, so the proof will be in whether it actually implements these suggestions. The choice to make its suggestions more transparent is not being made in a vacuum. Musk organized a flood of stories that he claimed would expose the platform's "free expression restriction" and has been outspoken in his criticism of how Twitter's former administration handled moderation and recommendation (Mostly, it just served to show how normal content moderation works.) Read More: Twitter “For You” page algorithm for iOS users is similar to TikTok But now that he's in charge, he's also faced a lot of criticism, from users upset that his tweets are being shoved in their faces by their For You pages to his conservative supporters growing increasingly worried about the little engagement they're receiving. He claims that the site's new recommendation algorithms "max deboost" offensive and hateful content, a claim that other researchers who lack access to the code have refuted. Additionally, the open-source community may present some competition for Twitter. A similar project named Bluesky, which is based on an open-source protocol, is backed by Twitter co-founder Jack Dorsey. Mastodon, a decentralized social network, has been gaining popularity in some circles.