UPDATED 11:15 EST / JULY 09 2015

NEWS

How League of Legends fights player abuse with machine learning

Riot Games has been facing a long uphill battle against League of Legends’ notoriously toxic player base, but it appears those efforts are finally paying off. According to Lead Game Designer Jeffrey Lin, Riot has successfully lowered abusive behaviors to just 2 percent of LoL matches through a combination of machine learning, game design, and community policies.

“As we spend more and more of our time online, we need to acknowledge that online harassment and toxicity is not an impossible problem, and that it is a problem worth spending time on,” Lin wrote in an article for Re/code. “For the past three years, a team of game designers and cross-discipline scientists at Riot Games have been doing just that, combining efforts to study online behavior in its game League of Legends.”

According to Lin, most of the negative behaviors displayed in the game came from regular players rather than trolls who are intentionally negative. In fact, 87 percent of all negative behaviors came from “neutral and positive citizens just having a bad day here or there.”

Lin explained that Riot did not want to invade users’ privacy by eliminating anonymity in the game, so the studio had to find another way to fight negative behaviors.

One solution to this problem was the creation of Tribunal, an auto-moderator system that generates public case files for players who are reported for “unacceptable” behaviors. Riot allowed other players to view these case files, which included game data and chat logs, and then vote on whether the behavior displayed was inappropriate or not.

After roughly 100 million player votes through the Tribunal system, Riot took that information and applied machine learning to quantify all of the words and behaviors that players considered to be negative. The studio teamed up with scientific teams around the world to review the data, and Lin explained that they discovered new insights into online behavior.

“We began to better understand collaboration between strangers, how language evolves over time and the relationship between age and toxicity,” Lin said. “Surprisingly, there was no link between age and toxicity in online societies.”

Lin had previously discussed LoL’s Tribunal system at GDC 2015, where he said, “When a society is silent, deviant behaviours emerge, and they become the norm, but if we can step in and stop that behavior from occurring, if we can identify that patient zero, then perhaps we can stop that spread from ever occurring.”

Image credit: Riot Games (c)

A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU