Maya Robertson
Social media company Twitter shared the source code for its recommendation algorithm on GitHub almost a year after its new owner Elon Musk said the platform should be open-source.
“Our initial release of the so-called algorithm is going to be quite embarrassing, and people are going to find a lot of mistakes, but we’re going to fix them very quickly’’, Musk said during a Twitter Space on Friday.
The same day, the company also shared a blog post explaining how its recommendation algorithm works.
‘’The foundation of Twitter’s recommendations is a set of core models and features that extract latent information from Tweet, user, and engagement data. These models aim to answer important questions about the Twitter network, such as, “What is the probability you will interact with another user in the future?” or, “What are the communities on Twitter and what are trending Tweets within them?” Answering these questions accurately enables Twitter to deliver more relevant recommendations.’’
Following the company’s announcement, Jane Manchun Wong said in a tweet that the algorithm ‘’specifically labels whether the Tweet author is Elon Musk’’, Democrat, Republican, or a ‘’Power User’’.
When asked about this, Musk said that the algorithm ‘’shouldn’t be dividing people into Republicans and Democrats’’. A company engineer later said that the labels are there for ‘’stat tracking purposes’’ and to ensure that they ‘’don’t bias towards one group versus another one”
Twitter Space ended shortly after Musk said he didn’t know his name was one of the four categories until then.
Meanwhile, the billionaire said in a tweet that they will make more parts of Twitter’s algorithm public in the future.
Comments
Loading…