A Framework for Cyberbullying Detection in Social Network

Abstract

Due to tremendous growth and popularity of current web technologies and social networking, online presence of the person has become permanent now. Through social networking connections, people usually express feelings, opinions, emotions and the most commonly seen is discussing the daily incidences which may include private or public talks. Especially in teenagers and young adults, expansion of social connections in terms of friendships has become fast without careful consideration of what is being shared and with whom. Such environment has become an avenue for cyber bullying, where abusive contents in terms of text messages or images are posted on the social network. For victims, this kind of behavior can lead to depression and other severe life-threatening problems. Therefore, measures need to be put in place to monitor and detect potentially harmful online activities. Manual check for all posts on social network is highly impossible because of large number of users. Therefore, in this paper, we have proposed a framework deployed for the detecting negative online interactions in terms of abusive contents carried out through text messages as well as images. The combination of text & image analysis techniques is considered as a suitable platform for the detection of potential cyber bullying threats.