Online social networks (OSNs) have seen a rapid growth in recent time. This growth in popularity has also paved the way for the threat of cyberbullying to grow to an extent that was never seen before. Cyberbullying is more alarming day by day in our present life. But the technical solution for preventing and detection of cyberbullying is very limited. Most of the studies on cyberbullying detection focus on detection, not prevention. In this paper, we show that the automatic cyberbullying detection both individual and group communication.

Keywords : Cyberbullying detection; SVM classifier; PSO-GA.