Spam Detection on Online Social Media Networks

Abstract

Now-a-days people are generally using social networking sites for communicating with the other users and for sharing information across the world. The online social networking sites are becoming the significant tools and are providing a common medium for number of users to communicate with each other. The large amount of information that is accessible on the social networking sites retain the cyber attackers, who generally exploit the information available for their benefits. They generally infect the user’s system, appeal the victims to click on malicious links, advertise some products only to gain money. Spam profiles are becoming major security threat used by cyber criminals and also a source of unwanted ads. Twitter is one among several social networking sites which are expanding on daily basis. Spam detection in twitter has become one of the major problems these days. A twitter spam account user nature is analyzed with a target to improve detection of social spam. An innovative technique based on deep learning technology is used for the identification of spam accounts in twitter. These techniques have an advantage that they use raw data to learn high level features on their own, unlike the traditional machine learning algorithms which require native features for the application of classification model.