Riot Games and Ubisoft recently announced “Zero Harm in Comms”, a research project jointly launched by the two game companies to combat harmful player interactions in game communities through artificial intelligence. The project aims to create a database to gather in-game data and train the AI-based preemptive moderation tools that detect and mitigate disruptive behavior in-game. Riot Games also stated that “Any data gathered that will be able to identify a person will be removed before sharing. ”
As members of the Fair Play Alliance, both companies believe that a zero-harm gaming community needs a joint effort across gaming companies. And with Riot Games’ reputation and the well-known titles of Ubisoft, there will surely be a wide range of player data included in the joint database to train the AI to mitigate disruptive communications.
“Disruptive player behaviours is an issue that we take very seriously but also one that is very difficult to solve,” said Yves Jacquier, executive director at Ubisoft La Forge. “There are keywords that can be immediately recognized as bad, but it’s often much trickier to parse. For example, if you see ‘I'm going to take you out’ in a chat, what does that mean? Is it part of the fantasy? If you’re playing a competitive shooter, it might not be a problem, but if it’s another type of game, the context might be totally different.”
Jacquier also stated that the goal is not to train the AI for every harmful scenario but to locate a specific example and detect those with high probability next time.
As of now, Jacquier has been working with Riot Games’ technology researcher Wesley Kerr on the “Zero Harm in Comms” project for about six months. They are also planning to share their experience with other companies in the gaming industry next year, hoping more of them can join this project.
“It's 2022,” says Jacquier. “Everyone is online, and everyone should feel safe, period.”
Source: Ubisoft News Riot Games News