Cyberbullying Detection based on text-stream classification

Current studies on cyberbullying detection, under text classification, mainly assume that the streaming text can be fully labelled. However, the exponential growth of unlabelled data in online content makes this assumption impractical. In this paper, we propose a session-based framework for automatic detection of cyberbullying from the huge amount of unlabelled streaming text. Given that the streaming data from Social Networks arrives in large volume at the server system, we incorporate an ensemble of one-class classifiers in the session-based framework. The proposed framework addresses the real world scenario, where only a small set of positive instances are available for initial training. Our main contribution in this paper is to automatically detect cyberbullying in real world situations, where labelled data is not readily available. Our early results show that the proposed approach is reasonably effective for the automatic detection of cyberbullying on Social Networks. The experiments indicate that the ensemble learner outperforms the single window and fixed window approaches, while learning is from positive and unlabelled data.