Using machine learning and other data signals, Twitter has hatched a plan to stop trolls spoiling healthy debate.
This includes people who have repeatedly tweeted at users who do not follow them, those who have often been blocked by other members of the site, or those who set up multiple accounts at once.
It actually sounds pretty simple at first: according to a Twitter blog post Tuesday, the company will simply organize conversations on Twitter differently based on "behavioral signals" created to root out trolls in "communal areas" of the social network. "Some troll-like behaviour is fun, good and humorous".
Twitter announced in a blog post today that it'll be implementing additional tools and signals to distinguish playful trolling from hateful, detractive comments that ruin the conversation.
"Some of these accounts and Tweets violate our policies, and, in those cases, we take action on them", he continued.
Facebook has not fully answered data privacy questions, say United Kingdom lawmakers
According to Facebook, the data breaches in question took place before the site's platform policies were changed in 2014. The question over how many clicks or swipes it takes for users to change their privacy settings was also dodged.
Twitter said it has tested the new approach and saw reductions in abuse complaints in conversations and in search.
The changes are a part of Twitter's efforts to increase the "health" of its platform.
Harvey and Gasca said that there are many new signals that Twitter is taking in, most of which are not visible externally. However, if they don't violate Twitter rules, they will still be visible if people click on "show more replies", the company said.
Gasca and Harvey don't say whether the proclaimed troll tweets would be demoted for everyone, or just for specific users they've been known to target. Although Twitter already has many guidelines in place that prevent harassment, Dorsey explained that Twitter's moderators will now be filtering tweets that display any abuse, making them appear less frequently in the feed. "We're encouraged by the results we've seen so far, but also recognize that this is just one step on a much longer journey to improve the overall health of our service and your experience on it".
"These accounts have a disproportionately large - and negative - impact on people's experience on Twitter", the company said in a statement. This technology and our team will learn over time and will make mistakes.