Analysis and detection of low quality information in social networks

Abstract

With social networks like Facebook, Twitter and Google+ attracting audiences of millions of users, they have been an important communication platform in daily life. This in turn attracts malicious users to the social networks as well, causing an increase in the incidence of low quality information. Low quality information such as spam and rumors is a nuisance to people and hinders them from consuming information that is pertinent to them or that they are looking for. Although individual social networks are capable of filtering a significant amount of low quality information they receive, they usually require large amounts of resources (e.g, personnel) and incur a delay before detecting new types of low quality information. Also the evolution of various low quality information posts lots of challenges to defensive techniques. My PhD thesis work focuses on the analysis and detection of low quality information in social networks. We introduce social spam analytics and detection framework SPADE across multiple social networks showing the efficiency and flexibility of cross-domain classification and associative classification. For evolutionary study of low quality information, we present the results on large-scale study on Web spam and email spam over a long period of time. Furthermore, we provide activity-based detection approaches to filter out low quality information in social networks: click traffic analysis of short URL spam, behavior analysis of URL spam and information diffusion analysis of rumor. Our framework and detection techniques show promising results in analyzing and detecting low quality information in social networks.