This is how Twitter will hide bad tweets in conversations and searches

Twitter, is beginning to use a wider range of signals to rank tweets in conversations and searches. The company said in a recent blog post that they will hide replies that are likely to be abusive comments from users that have often been blocked, muted, or reported for abuse will be less visible throughout the service.

Twitter has been ranking tweets in search and in conversations according to trends since the app was launched. The company has never taken negative signals into account when ranking them. This meant that replies could have easily be gamed by bad actors, whether they’re spammers hawking cryptocurrencies or bot networks attempting to influence elections.

CEO of Twitter Jack Dorsey says, “We are making progress as we go. The company plans to begin examining a much wider variety of signals when ranking tweets in conversations and in the search. The spirit of the thing is, we want to take the burden of the work off the people receiving the abuse or harassment.”

The company says that some of the signals it is going to examine include the number of accounts created by the person tweeting, IP address, and whether the tweet had led people to block the person tweeting it. Twitter won’t actually remove the tweets from Twitter, but they will now be moved to the “see more replies” section of the conversation, where they are hidden behind an additional tap. As you can see in the image below.

Twitter will be relying on algorithmic signals and it could have several advantages for the company as it works to reduce abuse on the platform. The algorithm works without respect to the content of the tweet, sparing Twitter from having to make tricky decisions around the tone or intent of a message. And it also works regardless of the language the tweet was written in, allowing the company to roll the changes out globally all at once.

These moves by Twitter are meant to address the company’s longstanding struggle to rein in abusive accounts. The company has previously made several high-profile moves over the past two years to make the service feel more civil but continues to draw criticism for its opaque policies and inconsistent enforcement.

Twitter issued a request for proposals from researchers and academics two months back to help the company measure the health of public conversations on the site and now those changes are being implemented by rolling out this update to all users globally.