A Design Approach for Automated Prevention of Cyberbullying Using Language Features on Social Media

Existing studies point out that the increased use of Information and Communication Technologies (ICT) has introduced new platforms, across which cyberbullying can occur. Most of the studies focus on the causes and consequences of cyberbullying among adolescents, however, few focus on the detection and prevention of cyberbullying, and even fewer focus on detecting cyberbullying in the Chinese language. Against this backdrop, an ethical approach to information filtering and regulation should be implemented and research into language features and language management is required. This research uses Sina Weibo as a case study, focusing on the features of language that occur in cyberbullying and the machine technique system that should be included as principles for managing and regulating cyberbullying contents on social media. Based on the Language Management Theory (LMT), inductive content analysis has been used to analyse offensive language features from the selected samples. The findings of this project will help refine theories, particularly those on offensive information and behaviour, and benefit academic understanding of cyberbullying and media, including the detection, regulation and governance.