Twitter Changes Algorithm To Tackle Trolling

Twitter says it is taking action against “trolls” that “distort and detract from the public conversation”, by making their tweets less perceptible.

Twitter has been trying to tackle abuse, harassment and intimidation on its platform for several years. The company said it would focus on “behavioral signals” to “improve the health” of discussions on the platform.

“People contributing to the healthy conversation will be more visible in conversations and search.”

Twitter said examples of suspicious behavior included:

accounts failing to confirm the email address they had signed up with
one person registering several accounts at the same time
a person repeatedly tweeting at people who did not follow them
It said a “majority” of complaints made by its users concerned less than 1% of the total number of accounts on the service. “These accounts have a disproportionately large – and negative – impact on people’s experience on Twitter,” said the company in a statement.

“The challenge for us has been: how can we proactively address these disruptive behaviors that do not violate our policies but negatively impact the health of the conversation.” Accounts exhibiting suspicious behaviors would now be “less visible” on the platform, it said, especially in public conversations and search results.

“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.”

Tests of the new system had resulted in fewer abuse reports being filed, suggesting people were having a “better experience.”