FILE PHOTO: A twitch login screen is seen at the offices of Twitch Interactive Inc, a social video platform and gaming community owned by Amazon, in San Francisco, California, U.S., March 6 2017. REUTERS / Elijah Nouvelage
November 30, 2021
By Elizabeth Culliford
(Reuters) – Amazon.com Inc’s live-streaming site, Twitch, is rolling out a tool to detect users trying to access channels they’ve been banned from, it said on Tuesday.
The new tool, called Detect Suspicious Users, will flag channel ban evaders as “likely” or “probable” so their creators and moderators can decide decide whether to take action or not.
Twitch has come under pressure from users to combat abusive practices on its site, including targeted harassment and so-called hate attacks, where chats by streamers flooded with harassing messages.
The platform, which is popular with video players, said it is rolling out the tool in response to user feedback about a need to find better ways to combat ban evaders.
“It’s addressing the core issue of targeted harassment,” Alison Huffman, Twitch’s director of public health product, said in an interview. “From talking to creators and their moderators, we have learned that this is a persistent issue for them.”
Huffman said the machine learning tool, which Twitch has been working on for several months, detects certain types of user behavior and account characteristics to flag potential ban evaders.
The tool will be enabled by default for all channels but can be adjusted or deactivated, Twitch said. It also says people can manually add users to tools they want to monitor more closely.
In September, Twitch added a way for creators and moderators to require phone and email verification before they can send chat messages, in a new anti-harassment measure. That month, it also filed in US federal court against two alleged adversaries.
Earlier this year, the company said it would ban users for serious misconduct happening to its platform.
Machine learning, a part of artificial intelligence, is the study of computer algorithms that can improve automatically through experience and by using data.
(Reporting by Elizabeth Culliford in New York; Editing by Kenneth Li and Matthew Lewis)
https://www.oann.com/twitch-launches-tool-to-catch-channel-ban-evaders/?utm_source=rss&utm_medium=rss&utm_campaign=twitch-launches-tool-to-catch-channel-ban-evaders Twitch launches tool to catch channel ban evaders
