Big Bird is watching: Twitter pecks at trolls who spoil conversations


Twitter announced today a new battle plan to combat trolls who "distort and detract from the public conversation".

When Twitter considers an account to be engaged in "trolling" bad behavior, it will display their tweets less and hide them in conversations.

Twitter is taking steps to deal with "troll" behaviour that "distort and detract" from the public conversation on the platform, changing how such tweets appear in public searches and conversations. The automated tools can also check on whether those users have ties to or interact with accounts that violate Twitter rules.

"There are many new signals we're taking in, most of which are not visible externally", said Del Harvey, vice president of trust and safety, and David Gasca, director of product management, health, in a blog post titled "Serving Healthy Conversation".

Abusive accounts, according to Dorsey, will be monitored by how often they tweet to someone who does not follow them, whether they have confirmed their email address, and if their language is appropriate. Some of these accounts and Tweets violate our policies, and, in those cases, we take action on them.

We don't know what Twitter will look like after this change, but the company says it's seen positive results in early testing, "resulting in a 4% drop in abuse reports from search and 8% fewer abuse reports from conversations".

Soros Foundation moves from Budapest to Berlin
Poland's Prime Minister Mateusz Morawiecki meets his Hungarian counterpart Viktor Orban in Warsaw, Poland May 14, 2018. Orban has accused Soros of being a part of a technique to flood Europe with migrants and of meddling in home affairs.

Twitter said it has tested the new approach and saw reductions in abuse complaints in conversations and in search. In other words, it's high time to confirm your email address on Twitter if you haven't yet.

"While still a small overall number, these accounts have a disproportionately large - and negative - impact on people's experience on Twitter", they said.

The company now uses a mixture of machine learning, human review processes and policies to determine how tweets are organised in conversations and search.

"This is only one part of our work to improve the health of the conversation and to make everyone's Twitter experience better".

"There will be false positives and things that we miss".

The company says it will deploy a screen saying "show more replies" in front of responses that its systems adjudicate as vexatious, cynical or calculated to offend. We'll continue to be open and honest about the mistakes we make and the progress we are making.