Cyberbullying detection using parent-child relationship between comments
Ziyi Li, Junpei Kawamoto, Yaokai Feng, Kouichi Sakurai · 2016
Cyberbullying is a underlying problem in social networking service, threatening users' mental and physical health. Previous research on automated cyberbullying detection is mostly textual or social based methods. Cyberbullying content is identified through a set of textual features within the content in the former method and through social information surrounding the content in the latter method. Those methods can not cater different cyberbullying standard for individual SNS user since each content is evaluated using same features. Therefore, in this article we propose a automated cyberbullying detection method that utilises the parent-child relationship between comments to capture the reaction from a third party to detect cyberbullying comments. We were able to improve the effectiveness of cyberbullying detection using only publicly available data.