Structure-Based Analysis of Different Categories of Cyberbullying in Dynamic Social Network

Abstract

Cyberbullying is the online fight between individuals or groups, and it can be viewed like harassment, rumor, denigration, exclusion, etc. Social networks are the main source of cyberbullying as various types of users interact with each other through text, audio, video, and images. One set of users uses the social media for the benefit of the whole society and the other set of users uses the social media for destructive purpose in the form of spreading rumors, harassment or to threaten others, etc., which is also called anomalous behavior. This article worked to detect the anomalous patterns using an exponential function and then proceeds to find the category of cyberbullying to which user belongs using subtractive clustering and fuzzy c-means clustering. The identification of category helps to find the extent to which these messages are harmful and based on which the culprit is apprehended or entrapped. State-of-the-art studies are focused on the detection of cyberbullying but this article captured different categories of cyberbullying.