Twitch’s AutoMod uses machine learning to help police chat

Plenty of Twitch streamers have built up solid, friendly communities for their respective channels but a lot of that comes down to active moderation within the chat itself. The larger the streamer, the more moderation required to keep the channel’s chat in accordance with the rules. Now it looks like Twitch wants to lessen some of that burden with AutoMod, a chat bot that uses machine learning and natural language processing to police chat rooms.

AutoMod isn’t necessarily intended to replace human moderators entirely, in-fact, Twitch’s tagline for the announcement is ‘Moderators are the sword, AutoMod is the shield’. Essentially, Mods will still be needed by streamers to help police chat, but AutoMod can flag up messages to be checked by a moderator before it is seen by the entire Twitch chat.

The announcement goes into detail on how streamers can customise AutoMod to suit their needs: “Streamers can configure AutoMod by selecting one of four levels. These levels affect how aggressively AutoMod holds back messages under four categories: identity, sexual language, aggressive speech, and profanity.”

“When AutoMod flags a message, it lets the original sender know that moderators will review the message’s content before it’s sent to chat. Meanwhile the message is shown to moderators, giving them a chance to accept or reject the message.”

Discuss on our Facebook page, HERE.

KitGuru Says: Being able to flag up specific messages before they are placed into the public Twitch chat sounds like a pretty useful tool. I imagine this will be particularly helpful when it comes to moderating the chat for large events, where thousands of messages are being sent at any given moment.

Become a Patron!