Automatic Detection and Prevention of Cyberbullying

The recent development of social media poses new challenges to the research community in analyzing online interactions between people. Social networking sites offer great opportunities for connecting with others, but also increase the vulnerability of young people to undesirable phenomena, such as cybervictimization. Recent research reports that on average, 20% to 40% of all teenagers have been victimized online. In this paper, we focus on cyberbullying as a particular form of cybervictimization. Successful prevention depends on the adequate detection of potentially harmful messages. However, given the massive information overload on the Web, there is a need for intelligent systems to identify potential risks automatically. We present the construction and annotation of a corpus of Dutch social media posts annotated with fine-grained cyberbullying-related text categories, such as insults and threats. Also, the specific participants (harasser, victim or bystander) in a cyberbullying conversation are identified to enhance the analysis of human interactions involving cyberbullying. Apart from describing our dataset construction and annotation, we present proof-of-concept experiments on the automatic identification of cyberbullying events and fine-grained cyberbullying categories.