Detecting Malicious Posts in Social Networks Using Text Analysis

Neeraja M, John Prakash

Abstract: We have reached the era of social media networks represented by Facebook, Twitter, Flicker and YouTube. Internet users spend most of their time on social networks than search engines. Public figures and business entities set up social networking pages to promote direct interactions with the online users. Social media systems heavily depend on users for getting content and sharing. Information used is spread across the social networks in quick and effective manner. However, at the same time social media networks become vulnerable to different types of unwanted and malicious hacker or spammer actions. 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. In this work we develop a detection mechanism to distinguish between malicious and genuine posts within seconds after the posts are uploaded by user. This work proposes an extensive set based on the textual content and URL features to identify malicious content on Facebook at zero time. The intent is to catch malicious or vulgar content that is currently evading Facebooks detection mechanisms.

Keywords: Social Network, Text Analysis, Similarity, Suspicious Post, Suspicious URL, Cybercriminals