Twitter is a home for nasty tweets. The company has done a lot of things, but with little results. But in an updated policy, Twitter wants to change that.
The strategy here, is fighting abusive trolling by burying their tweets, making them less visible in conversations and search results, even if these individual tweets don't violate Twitter's policies.
So instead of banning these trolls' tweets or the users, Twitter wants to hide them from view.
"Less than 1% of accounts make up the majority of accounts reported for abuse, but a lot of what’s reported does not violate our rules," said Twitter. "While still a small overall number, these accounts have a disproportionately large – and negative – impact on people’s experience on Twitter."
Today we are introducing new behavior-based signals into how Tweets are organized and presented in areas like conversations and search.
This is to improve the health of the conversation and improve everyone’s Twitter experience.— Twitter Safety (@TwitterSafety) May 15, 2018
To make this happen, Twitter uses algorithms and machine learning to detect suspicious behavior and patterns regardless of the people or the content of the actual tweets.
The behavior and patterns are common with troll-like accounts. For example, users who open up accounts without verifying their email address, those who open up multiple accounts at the same time, and users who repeatedly tweet at someone who doesn’t follow them.
"We’re also looking at how accounts are connected to those that violate our rules and how they interact with each other," the company said.
Because these "signals" can be identified by an algorithm, they can be tied to behavior and not the content of the tweets themselves.
When Twitter's algorithms spot a troll-like behavior, it will place the said user under a sort of quarantine. Here, all of their interactions will be invisible to other users, unless those users press the "show more replies" button underneath a tweet.
The company has been testing this kind of muting in selected markets for a couple of months, and saw a notable drop in abuse reports. This suggests that tweets from trolls that were hidden, won't disrupt conversation because no one can practically see them.
"We’ve already seen this new approach have a positive impact, resulting in a 4% drop in abuse reports from search and 8% fewer abuse reports from conversations. That means fewer people are seeing Tweets that disrupt their experience on Twitter," explained Twitter
This strategy adds to Twitter's previous attempts in the past.
"Our work is far from done."