Although this is probably less research-y than usual posts to this list but I thought the use of ML to analyze a community curated corpus of positive and negative online behavior was interesting:
http://recode.net/2015/07/07/doing-something-about-the-impossible-problem-of...
-Toby
Very interesting article, thanks Toby. Forwarding this on.
I particularly like this paragraph: "As a result of these governance systems changing online cultural norms, incidences of homophobia, sexism and racism in League of Legends have fallen to a combined 2 percent of all games. Verbal abuse has dropped by more than 40 percent, and 91.6 percent of negative players change their act and never commit another offense after just one reported penalty."
Pine
On Fri, Nov 13, 2015 at 1:06 PM, Toby Negrin tnegrin@wikimedia.org wrote:
Although this is probably less research-y than usual posts to this list but I thought the use of ML to analyze a community curated corpus of positive and negative online behavior was interesting:
http://recode.net/2015/07/07/doing-something-about-the-impossible-problem-of...
-Toby
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
Wow. That's really interesting, thanks for sharing.
I think beyond the specific measures that they used, just making the decision from the administration to identify and fix harassment problems probably made a big difference on its own. Nobody had ever mentioned to that kid not to use the N word? Just clearly stating the principles is a good idea.
On Fri, Nov 13, 2015 at 1:33 PM, Pine W wiki.pine@gmail.com wrote:
Very interesting article, thanks Toby. Forwarding this on.
I particularly like this paragraph: "As a result of these governance systems changing online cultural norms, incidences of homophobia, sexism and racism in League of Legends have fallen to a combined 2 percent of all games. Verbal abuse has dropped by more than 40 percent, and 91.6 percent of negative players change their act and never commit another offense after just one reported penalty."
Pine
On Fri, Nov 13, 2015 at 1:06 PM, Toby Negrin tnegrin@wikimedia.org wrote:
Although this is probably less research-y than usual posts to this list but I thought the use of ML to analyze a community curated corpus of positive and negative online behavior was interesting:
http://recode.net/2015/07/07/doing-something-about-the-impossible-problem-of...
-Toby
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
Wiki-research-l mailing list Wiki-research-l@lists.wikimedia.org https://lists.wikimedia.org/mailman/listinfo/wiki-research-l
wiki-research-l@lists.wikimedia.org