An Effective Approach for Cyberbullying Detection

The rapid growth of social networking is supplementing the progression of cyberbullying activities. Most of the individuals involved in these activities belong to the younger generations, especially teenagers, who in the worst scenario are at more risk of suicidal attempts. We propose an effective approach to detect cyberbullying messages from social media through a weighting scheme of feature selection. We present a graph model to extract the cyberbullying network, which is used to identify the most active cyberbullying predators and victims through ranking algorithms. The experiments show effectiveness of our approach. KeywordsSocial Networks; Cyberbullying; Text-Mining; Link Analysis