Twitter got better one of the many promises made by CEO Elon Muskposting on Friday afternoon what is claimed to be the tweet recommendation algorithm code. on GitHub.
The code posted under GNU Affero General Public License v3.0contains numerous details about what factors make a tweet more or less likely to appear in a user’s timeline.
IN blog post accompanying code release, Twitter’s engineering team (without a caption) notes that the system for determining which “most popular tweets end up on your device’s For You timeline” “consists of many interconnected services and tasks.” Every time the Twitter home screen is refreshed, Twitter pulls “the top 1,500 tweets from hundreds of millions,” the post says.
The largest source of these tweets are “online sources” or users who are being followed by someone. The top tweets from this stack are ranked by the likelihood of a user interacting with the author of that tweet; the more likely their tweets are to appear in For You. For “offline sources” not followed by the user, Twitter says it considers tweets that get the attention of people the user follows and tweets that are liked by those who like tweets similar to the user.
Already those who have looked at the code have noticed considerations that raise many more questions. Many posted them, of course, on Twitter itself.
Twitter just released the source code of the “algorithm”.
Oh what is this file? Predicates for tweets on home timeline?
Oh what is that second picture? pic.twitter.com/UE3dU8e3Os
— Olafur Waage (@olafurw) March 31, 2023
Olafur Vaage, senior software engineer at Norwegian consulting service TurtleSec, noted that inside “HomeTweetTypePredicates.scala.” some of the apparent reasons for a tweet to be a candidate for the “For You” section:
Elsewhere in the code code comment presumably left by a Twitter engineer, explains that these identification values are “used solely for collecting metrics.” The comment goes like this:
These author ID lists are used solely for collecting metrics. We track how often we serve tweets from these authors and how often their tweets impress users. This helps us confirm on our A/B experimentation platform that we’re not submitting changes that negatively impact one group over others.
The names of the objects in question, such as “DDGStatsDemocratsFeature” or “DDGStatsElonFeature” seem to support this interpretation, but this may not be possible to confirm with available code. However, it is interesting that Twitter checks and correlates these variables. During the Twitter Spaces audio session, a Twitter engineer noted that the labels used for the metrics were Democrats and Republicans. Musk, who claimed he didn’t know about the labels until today, suggested they shouldn’t be there.
Other factors are also taken into account for a tweet: its age is less than 30 minutes, the presence of images, and whether it comes from a “power user”. some believe means “legacy” verified account.
Today, most of the recommendation algorithm will be made open source. The rest will follow.
The acid test is that independent third parties must be able to determine with reasonable accuracy what is likely to be shown to users.
Surely there will be many awkward moments… https://t.co/41U4oexIev
— Elon Musk (@elonmusk) March 31, 2023
Musk tweeted along with a company blog post that a recommendation algorithm stating an “acid test” would be if “independent third parties” could “determine with reasonable accuracy what users are likely to be shown.”
Twitter’s release of its algorithm code comes just days after the social network’s broader source code was discovered on GitHub, potentially sitting there for months. according to the New York Times. Twitter then received a subpoena forcing GitHub to reveal information about the GitHub poster.
A report by Platformer earlier this week said that Twitter used a secret list of 35 top Twitter users, including President Biden, LeBron James, Ben Shapiro and Musk. Evidence of the implementation of this list, reportedly prompted in part by Musk’s dissatisfaction with his own involvement, has yet to be found in a codebase posted on Twitter.
Specifically, the code arrives just hours before “verified legacy” users – those who were blue-checked to indicate authenticity or notoriety before Musk bought the service – are due to be canceled in favor of paid ones. Twitter Blue followers. Although some users associated with governments and large organizations may apply for ticks of other colorsonly Twitter Blue subscribers for $8 per month will receive “priority rating in conversations.” among other features.
All of these changes take place on April 1, or April Fool’s Day.