Fighting trolling with academic rigour

Trolling – hostile, provocative anti-social behaviour – is one of the biggest challenges to any large-scale online community – and that includes comment sections on mainstream publications.

The problem is far, far bigger in the online gaming world, though. And one of the biggest games in the eSports sector – League of Legends – suffers particularly badly. The game’s publisher – Riot – is fighting back with huge studies, conducted with academic rigour, and shared with the academic community:

“We let loose machine learning,” Lin says. The automated system could provide nearly instantaneous feedback; and when abuse reports arrived within 5–10 minutes of an offence, the reform rate climbed to 92%. Since that system was switched on, Lin says, verbal toxicity among so-called ranked games, which are the most competitive — and most vitriolic — dropped by 40%. Globally, he says, the occurrence of hate speech, sexism, racism, death threats and other types of extreme abuse is down to 2% of all games.

2% is still substantial, but the approach here is certainly one community managers across the journalism world could learn from.