BullyBlocker: toward an interdisciplinary approach to identify cyberbullying

• Published in: Social network analysis and mining Vol. 8; no. 1; p. 18
• Main Authors: Silva, Yasin N., Hall, Deborah L., Rich, Christopher
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.12.2018; Springer Nature B.V
• Subjects: Accuracy; Adolescents; Applications of Graph Theory and Complex Networks; Applications programs; Automation; Bullying; Children & youth; Computer Science; Cyberbullying; Data Mining and Knowledge Discovery; Digital media; Drug use; Economics; Game Theory; Girls; Humanities; Identification; Interdisciplinary aspects; Law; Machine learning; Mass media; Mental depression; Methodology of the Social Sciences; Mobile computing; Networking; Original Article; Parents; Psychological research; Psychology; Social and Behav. Sciences; Social networks; Statistics for Social Sciences; Teenagers; Young adults; Youth; Cyberbullying; Psychology; Automated identification; Social networks; Vulnerability factors; Cyberbullying factors; Facebook
• ISSN: 1869-5450; 1869-5469
• DOI: 10.1007/s13278-018-0496-z

Cyberbullying is the deliberate use of online digital media to communicate false, embarrassing, or hostile information about another person. It is the most common online risk for adolescents, yet well over half of young people do not tell their parents when it occurs. While there have been many studies about the nature and prevalence of cyberbullying, there have been relatively few in the area of automated identification of cyberbullying that integrate findings from computer science and psychology. The goal of our work is thus to adopt an interdisciplinary approach to develop an automated model for identifying and measuring the degree of cyberbullying in social networking sites, and a Facebook app, built on this model, that notifies parents about the likelihood that their adolescent is a cyberbullying victim. This paper describes the challenges associated with building a computer model for cyberbullying identification, presents key results from psychology research that can be used to inform such a model, introduces a holistic model and mobile app design for cyberbullying identification, presents a novel evaluation framework for assessing the effectiveness of the identification model, and highlights crucial areas of future work. Importantly, the proposed model—which can be applied to other social networking sites—is the first that we know of to bridge computer science and psychology to address this timely problem.