Twitter is finally doing something about trolls -- using 'behavioral signals'

Andrew Cummings
May 16, 2018

Essentially, Twitter is making a strong effort to distinguish itself from its competitors right now, particularly since we live in a post-Cambridge Analytica world, where social media platforms must convince their customers that the integrity and quality assurance inherent to their services remain protected and secure at all costs.

Using machine learning and other data signals, Twitter has hatched a plan to stop trolls spoiling healthy debate.

Behavioral signals that can identify trolls, according to Twitter, include accounts failing to confirm their email address when they sign up, a person registering several accounts at once, a person repeatedly tweeting at people they don't follow, or joining in a "coordinated attack" with other users.


"Because this content doesn't violate our policies, it will remain on Twitter, and will be available if you click on "Show more replies" or choose to see everything in your search setting", said a joint statement by Del Harvey, Twitter's vice president on trust and safety and David Gascam, Twitter's director of product management with responsibility for health. "Some troll-like behaviour is fun, good and humorous".

"Now, we're tackling issues of behaviours that distort and detract from the public conversation in those areas by integrating new behavioural signals into how tweets are presented", Twitter said. Some of these accounts and Tweets violate our policies, and, in those cases, we take action on them.

Twitter says its testing has shown positive results, with a 4% drop off in reported abuse from search and 8% fewer reports of abuse from within conversations. Twitter will look for signals such as unconfirmed email addresses, multiple accounts opened by the same user, and repeated interactions with accounts that don't follow them. And, while Marvey and Gasca acknowledge their work is far from done, they said early tests are promising.


Additionally, following Facebook's lead, Twitter recently began encouraging a public conversation about its impact on the health of individuals and society at large.

"That means fewer people are seeing Tweets that disrupt their experience on Twitter", the post said.

"This technology and our team will learn over time and will make mistakes", the post said.


Twitter executives Harvey and Gascam said that the initiative is part of an ongoing attempt "to improve the health of the public conversation on Twitter". Our goal is to learn fast and make our processes and tools smarter.

Other reports by iNewsToday

FOLLOW OUR NEWSPAPER