Twitter is testing new tools to expand recommendations, allowing users to remove irrelevant tweets from the timeline

Twitter Tests New Tools to Expand Recommendations, Allows Users to Remove Unrelated Tweets From Timeline

Twitter is expanding how users recommend posts from accounts they don’t follow, the social media company announced Tuesday. As part of the expansion, it’s also creating tools for users to moderate and provide feedback on that content.

“With millions of people signing up for Twitter every day, we want to make it easy for everyone to connect with the accounts and topics they’re interested in,” Twitter said in a letter. Blog post,

The tests came as social media companies doubled down this year on what social media companies called “unconnected content,” or posts from accounts users don’t follow, after the tiny video app TikTok gained popularity for relying entirely on algorithm-driven suggestions.

Angela Wise, senior director of product management responsible for “discovery” on the service, said one of the new designs Twitter is testing is the placement of “related tweets” below conversations on the tweet details page.

Twitter is also experimenting with an “X” tool that users can click to remove recommended tweets they don’t like from their timelines, the blog post said.

Competitor Meta Platform is aiming to double the percentage of recommended content filling users’ feeds on Facebook and Instagram by the end of 2023, it revealed in July.

Twitter has been making less wholesale changes than that, adopting Recommended Tweets in its home timeline as of 2014, though some of its redesigns have similarly included a nod to TikTok.

In a recent experiment offering a choice between algorithmic and chronological versions of his home timeline, he renamed the algorithmic version “For You,” the same as TikTok’s homepage.

Twitter’s Wise said the company’s discovery efforts are largely aimed at new users, who haven’t yet figured out which accounts to follow and typically send fewer signals about their interests to the company than longtime tweeters.

Some users have had “relevant tweets” exposing them to unrelated hyperpartisan content and causing confusion about which tweets are part of the conversation and which were suggested by the algorithm.



LEAVE A REPLY

Please enter your comment!
Please enter your name here