SpADe: Multi-Stage Spam Account Detection for Online Social Networks

In recent years, Online Social Networks (OSNs) have radically changed the way people communicate. The most widely used platforms, such as Facebook, Youtube, and Instagram, claim more than one billion monthly active users each. Beyond these, news-oriented micro-blogging services, e.g., Twitter, are daily accessed by more than 120 million users sharing contents from all over the world. Unfortunately, legitimate users of the OSNs are mixed with malicious ones, which are interested in spreading unwanted, misleading, harmful, or discriminatory content. Spam detection in OSNs is generally approached by considering the characteristics of the account under analysis, its connection with the rest of the network, as well as data and metadata representing the content shared. However, obtaining all this information can be computationally expensive, or even unfeasible, on massive networks. Driven by these motivations, in this article we propose SpADe, a multi-stage Spam Account Detection algorithm with reject option, whose purpose is to exploit less costly features at the early stages, while progressively extracting more complex information only for those accounts that are difficult to classify. Experimental evaluation shows the effectiveness of the proposed algorithm compared to single-stage approaches, which are much more complex in terms of features processing and classification time.

Automated summary

In recent years, Online Social Networks (OSNs) have revolutionized communication, with platforms like Facebook, Youtube, and Instagram boasting over one billion monthly active users each. Micro-blogging services like Twitter are also popular, with over 120 million users daily sharing global content. Unfortunately, OSNs are plagued by both genuine and malicious users, with the latter spreading unwanted, harmful, and discriminatory content. This article proposes SpADe, a multi-stage spam account detection algorithm that leverages less expensive features initially and extracts complex information only for challenging accounts. Experimental evaluation shows the superiority of this approach over single-stage methods in terms of feature processing and classification time complexity.