Malicious Posts Detection Using Emotions and Reputation on Facebook Data

Abstract

Online Social Networks (OSNs) witness a rise in user activity whenever an event takes place. Malicious entities exploit this spur in user-engagement levels to spread malicious content that compromises system reputation and degrade user experience and has recently been reported to face much abuse through scams and other type of malicious content, especially during news making events. It has been observed that there is a greater participation in Facebook pages regarding malicious content generation.

These contents will be in greater amount as compared to legitimate content. These issues are addressed in this research work, whose main goal is to detect the malicious activities involved in the social web pages accurately. In the proposed research method, Reputation and EMOtional (REMO) score based malicious post detection framework is introduced. This method combines the power of reputation score observed through WOT and the emotional score obtained from the annotation profile of the post. Annotation in the Facebook data refers to the user’s emotion about the post such as like, dislike, angry and so on. In this case, posts that receive more dislikes are probably malicious. Similarly, posts with no annotation also likely to be verified as malicious. The overall implementation evaluation of the proposed research method is done in the python simulation environment from which it can be proved that the proposed work can provide optimal outcome than the existing research methods.