To make sure you never miss out on your favourite NEW stories, we're happy to send you some reminders

Click 'OK' then 'Allow' to enable notifications

20,000 Toxic 'CS:GO' Players Banned In Six Weeks By New AI

20,000 Toxic 'CS:GO' Players Banned In Six Weeks By New AI

CS:GOing, going, gone.

Ewan Moore

Ewan Moore

In a move that's sure to be remembered as a crucial step in the journey to machines rising up against man and taking over the planet in a fiery revolution, a new AI built specifically to trawl chat messages and ban toxic Counter-Strike: Global Offensives has managed to weed out 20,000 players within its first six weeks.

I'll give you a second to get over the shocking revelation that CS:GO is filled with toxic players, shall I?

CS:GO /
Valve

As reported by PCGamesN, this vital new AI is called Minerva, and was built by a team over at FACEIT, the online gaming platform responsible for organising the 2018 CS:GO London Major.

FACEIT worked in collaboration with Google Cloud and Jigsaw to develop the AI, with the idea that it could fight toxicity in online gaming by analysing messages in a game's text chat and identifying toxic players and behaviours.

Minerva first started looking at CS:GO chat messages towards the end of August, and managed to mark an astounding 7,000,000 messages as toxic, issuing 90,000 warnings and banning 20,000 players in the process. Imagine what it could do in a year.

Minerva was trained through machine learning, and was able to hand out warnings for verbal abuse and flag spam messages. Almost as soon as a match of CS:GO ended, the AI was could send players messages either warning or banning them outright based on the severity or frequency of their behaviour.

CS:GO /
Valve

It seems that Minerva has already had a positive tangible effect, as it's been reported that the number of toxic messages in CS:GO dropped by 20 percent while the AI was in use, with the number of unique players sending those messages reportedly fell by 8 percent.

This is just the first step on Minerva's journey to stamp out toxicity in online gaming, as FACEIT explained in a blog post taking stock of the AI's success so far and intentions going ahead.

"In-game chat detection is only the first and most simplistic of the applications of Minerva and more of a case study that serves as a first step toward our vision for this AI," they wrote.

CS:GO /
Valve

"We're 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 behaviors in real-time."

"In the coming weeks we will announce new systems that will support Minerva in her training."

Featured Image Credit: Valve

Topics: CS:GO, Valve, Steam