Reuters-Amazon.com Inc's live-streaming site, Twitch, is launching a tool to detect users who try to access channels where they have been banned, it said on Tuesday.
The new tool, called Suspicious User Detection, will flag possible channel ban evaders, so that creators and moderators of those channels can decide whether to take action.
Users have been pressured to fight abuse on its site, such as targeted harassment and so-called hate raids, where streamers' chats are flooded with harassing messages.
The platform, which is popular with video gamers, said it was launching a tool in response to user feedback on the need for ways to combat ban evaders.
Alison Huffman, Twitch's director of product for community health, said in an interview that it is addressing the core problem of targeted harassment. We have heard from conversations with creators and their moderators that this is a persistent problem for them. Huffman said that the machine learning tool that Twitch has been working on for several months detects certain types of user behavior and characteristics of accounts to flag potential ban evaders.
The tool will be turned on for all channels but can be deactivated or adjusted, according to Twitch. It said it was possible to add manually to the tool users they want to monitor more closely.
In September, Twitch added a way for moderators to require phone and email verification before they can send chat messages, a new anti-harassment measure. It filed a complaint in the U.S. federal court on two alleged hate raiders last month.
The company said it would ban users for misconduct that occurred away from its platform earlier this year.
Machine learning is the study of algorithms that can be improved automatically through experience and the use of data.