Sometimes if not most of the times, people on the web are not going to do what they are told to do.
There are many reasons for this. But most of the time, it's because there is not law that can prevent them from doing what they want, and also because it's so easy for users to bypass the rules platforms are imposing to them.
And Twitch, the platform popular for streaming games among gamers around the world, is experiencing issues related to this.
From hate raid campaigns and more, Twitch users could get away easily, and return when they have the chance to cause more damage.
To ramp up its attempt in finding those who tend to avoid bans, Twitch is introducing an AI feature to help streamers protect their channels.
Dubbed the "Suspicious User Detection," the tool is meant to automatically flag individuals it suspects may be "likely" or "possible" ban dodgers.
For those who are "likely" ban dodgers, Twitch will prevent them from sending messages that would show up in chat. Furthermore, whenever the AI catches one, Twitch will also identify the individual to the Creators and Mods.
After that, the streamer can decide whether they want to ban that person.
And as for those "possible" ban evaders, Twitch will allow their messages to pass through the chat like normal, but behind their backs, Twitch will flag the accounts in question, and will notify both the Creator and their Mods so they can monitor the user and restrict them from chatting if needed.
"You can also adjust how messages from each group are treated — for example if you want to be extra cautious, you can restrict messages from both likely and possible ban evaders from appearing in Chat," Twitch explained in a website post.
"The tool is powered by a machine learning model that takes a number of signals into account — including, but not limited to, the user's behavior and account characteristics — and compares that data against accounts previously banned from a Creator's channel to assess the likelihood the account is evading a previous channel-level ban," explained a Twitch spokesperson.
"This tool was inspired in large part by community feedback around the need for better ways to curb ban evaders."
"When we were speaking with mods about their pain points, we heard that it can be hard to distinguish whether a user who chatted something that violated their channel’s norms was a harmful, repeat harasser or just a newer viewer who hadn’t learned that channel’s customs yet. As such, we designed this tool to give mods and creators more information about potential ban evaders so they could make more efficient and informed decisions within their channel."
Suspicious User Detection, powered by machine learning, is here to help you identify and restrict suspected channel ban evaders from chatting before they can disrupt your stream.
Learn more here: https://t.co/01cCwnQZfw pic.twitter.com/QWVSnRPg1X— Twitch (@Twitch) November 30, 2021
Twitch is turning on this Suspicious User Detection by default on all channels, so streamers can focus more on their content and their communities.
Streamers can turn it off if they want to.
"You can also manually add users that you’d like to monitor more closely, either from the user’s Viewer Card or the new Suspicious Users widget in Mod View," added Twitch.
It should be noted that the feature is not perfect, and may have issues here and there.
This is because by design, it's practically impossible for Twitch to catch all ban dodgers. AI cannot be made a 100% accurate in every context, meaning that there will be some that can slip through the cracks.
In other words, there is a possibility of false positives and false negatives.
"You're the expert when it comes to your community, and you should make the final call on who can participate," the company said.
Adding that because the tool uses AI, "the tool will learn from the actions you take and the accuracy of its predictions should improve over time as a result."