Automatic analysis and identification of verbal aggression and abusive behaviors for online social games
作者：
Highlights：
• We propose a system to automatically evaluate player complaints in a social game.
• Our database contains 100,000 players, 1000 complaints and 240 abusive players.
• We experiment with several pieces of player information and their combinations.
• Our system can correctly identify abusive players with up to 85% precision.
• We can isolate and identify severe abuse cases with a higher confidence.
摘要
•We propose a system to automatically evaluate player complaints in a social game.•Our database contains 100,000 players, 1000 complaints and 240 abusive players.•We experiment with several pieces of player information and their combinations.•Our system can correctly identify abusive players with up to 85% precision.•We can isolate and identify severe abuse cases with a higher confidence.
论文关键词：Online social games,Sociability,Verbal aggression,Abusive behavior,Chat analysis,Cyberbullying,Machine learning
论文评审过程：Received 2 October 2013, Revised 31 August 2014, Accepted 6 October 2014, Available online 20 November 2014, Version of Record 11 September 2015.
论文官网地址：https://doi.org/10.1016/j.chb.2014.10.025
