Can data science be used to encourage better user behavior? A number of experiments with League of Legends show perhaps it can:
But Beck and Merrill decided that simply banning toxic players wasn’t an acceptable solution for their game. Riot Games began experimenting with more constructive modes of player management through a formal player behavior initiative that actually conducts controlled experiments on its player base to see what helps reduce bad behavior. The results of that initiative have been shared at a lecture at the Massachusetts Institute of Technology and on panels at the Penny Arcade Expo East and the Game Developers Conference. (post)
The first change they made was to turn off cross-team chat as a default. This dramatically reduced negative chat while keeping use of cross-team chat stable.
The second thing they did was to compile dictionaries of words the negative players would use that were not used by positive players. “It turns out that if you use the dictionaries, you can predict if a player will show bad behavior with up to 80 percent accuracy from just one game’s chat log,” Lin said.
The third thing they did was make the banning process more informational, showing banned members precisely what they were banned for, and what level of agreement was show on the ban.