Google and Faceit team up to ban 20,000 CS-GO players in 42 days.

Many players who play Counter-Strike: Global Offensive have ran into toxic frustrating players. To begin cracking down on this Google and Faceit came together to create a chat AI called “Minerva”.

Minerva analyzes chat messages and bans toxic players automatically.

Minerva has processed 7,000,000 mmessages and sent warnings to 90,000 users! Over 20,000 users have been banned.

They claim that the percentage of toxic messages has dropped by 20% in August and September. The system seems to be very successful.

So how does Minerva work?

Minerva identifies toxic behavior as it is happening in a match. It then ensures that if a player behaves in a toxic manner action is taken immediately. The player is provided with feedback on what they did wrong so they can correct their behavior in the future. Repeat offenses within short periods of time get harsher punishments.

Minerva abuse alert

“In-game chat detection is only the first and most simplistic of the application of “Minerva” and more of a case study that serves as the first step towards our vision for this AI.

We are really excited about this foundation as it represents a strong base that will allow us to improve Minerva until we finally detect and address all kinds of abusive behaviours in real-time.

“In-game chat detection is only the first and most simplistic of the application of “Minerva” and more of a case study that serves as the first step towards our vision for this AI.

We are really excited about this foundation as it represents a strong base that will allow us to improve Minerva until we finally detect and address all kinds of abusive behaviours in real-time.

In the coming weeks, we will announce new systems that will support Minerva in her training “

Faceit stated in their Blog

More work is being done to make the AI more accurate and clean up the toxicity in Counter-strike: Global Offensive. This sounds like they are off to a great start though!

Check out FaceIT’s blog post here!

0 0 vote
Article Rating
Subscribe
Notify of
0 Comments
Inline Feedbacks
View all comments
0
Would love your thoughts, please comment.x
()
x