An Algorithm that identifies Bullies on Twitter with 90% accuracy.

New York: Machine learning algorithms have been developed by scientists which can predict bullying and aggressors on Twitter with 90% accuracy.
The study analyzed the behavioral patterns showed by abusive Twitter users as well as the differences of theirs from various other Twitter users.
“Tweets of twitter users have been gathered along with their profiles, and social network-related things like who they follow, who follows them,” said Jeremy Blackburn, Binghamton University.
The scientists created algorithms to automatically classify 2 specific kinds of offensive online behavior, i.e. cyberbullying and cyberaggression. The algorithms could determine abusive users on Twitter with accuracy up to 90%, scientists said.
With this algorithm, abusive users were able to identify with 90% accuracy.