Twitch Provides Update on Fighting Against Malicious Bot Attacks
Twitch recently released an update on its ongoing efforts to combat hate raids and malicious bot attacks on its platform. These attacks, which have become a pervasive problem across the internet, particularly affect Black and LGBTQIA+ creators. However, Twitch reports a significant decline in hate raid reports this year, down by 97% since the surge experienced in September 2021.
New Tools and Machine Learning Models
Twitch credits this decline to the introduction of new and updated machine learning models that effectively block and prevent harassment. The platform’s proactive measures have already resulted in the blocking of over 75 million potentially harmful messages in 2022. While it’s unclear how many of these messages were directly related to botting or hate raids, Twitch’s efforts remain focused on creating a safer environment for its community.
Continued Efforts and Acquisitions
In addition to implementing machine learning models, Twitch reflects on its ongoing efforts to improve platform safety. The recent acquisition of Spirit AI will help enhance auto-moderation in channels, further refining the platform’s ability to combat undesirable behavior. Twitch has also introduced various features since last year, including ban evasion detection, shared ban information, and verified chatting.
Introducing Shield Mode
Excitingly, Twitch plans to launch a new tool called “Shield Mode” on Wednesday, November 30. While details about this tool are currently scarce, Twitch promises to provide more information when it is officially unveiled later this week. It’s clear that Twitch is committed to staying ahead of bad actors and continuously improving its platform’s safety features.