Twitch Launches Hate Speech Detector Tool

Gamers, can now avoid the perpetrators of hate speech who have been banned on Twitch. (photo: doc. pixabay)

JAKARTA - Amazon.com Inc's live streaming site Twitch has launched a tool to detect users trying to access channels where they have been banned. This feature goes into use on Tuesday, November 30.

The new tool, called Suspicious User Detection, will flag channel ban evaders as "likely" or "possible", so channel creators and moderators can decide whether to take action.

Twitch has now come under pressure from users to combat abuses on its site, including targeted harassment and so-called hate attacks in which chat streamers are flooded with harassing messages.

The platform, popular with video gamers, said it launched the tool in response to user feedback on the need for ways to better combat ban evaders.

"This addresses the core issue of targeted harassment," Alison Huffman, Twitch's director of product for public health, said in an interview. "We have heard through conversations with content creators and their moderators from time to time that this is a persistent problem 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 disabled, says Twitch. It also says people can manually add users of the tools they want to monitor more closely.

In September, Twitch added a way for creators and moderators to request phone and email verification before they can send chat messages, in a new anti-harassment measure. That month, he also filed a complaint in US federal court against two suspected hate speech abusers.

Earlier this year, the company said it would ban users for serious violations that occur outside of its platform.

Machine learning, a subset of artificial intelligence, is the study of computer algorithms that can be improved automatically through experience and with the use of data.