Detecting malicious users in the social networks using machine learning approach

Abstract

Social networking plays a very important role in today's life. It helps to share ideas, information, multimedia messages and also provides the means of communication between the users. The popular social medias such as Facebook, Twitter, Instagram, etc., where the billions of data are being created in huge volume. Every user has their right to use any social media and a large number of users allowed malicious users by providing private or sensitive information, which results in security threats. In this research, they are proposing an natural language processing (NLP) technique to find suspicious users based on the daily conversations between the users. They demonstrated the behaviour of each user through their anomaly activities. Another machine learning technique called support vector machine (SVM) classifiers to detect the toxic comments in the comments blog. In this paper, the preliminary work concentrates on detecting the malicious user through the anomaly activities, behaviour profiles, messages and comment section.