Addressing the new generation of spam (Spam 2.0) through Web usage models

Abstract

New Internet collaborative media introduce new ways of communicating that are not immune to abuse. A fake eye-catching profile in social networking websites, a promotional review, a response to a thread in online forums with unsolicited content or a manipulated Wiki page, are examples of new the generation of spam on the web, referred to as Web 2.0 Spam or Spam 2.0. Spam 2.0 is defined as the propagation of unsolicited, anonymous, mass content to infiltrate legitimate Web 2.0 applications.The current literature does not address Spam 2.0 in depth and the outcome of efforts to date are inadequate. The aim of this research is to formalise a definition for Spam 2.0 and provide Spam 2.0 filtering solutions. Early-detection, extendibility, robustness and adaptability are key factors in the design of the proposed method.This dissertation provides a comprehensive survey of the state-of-the-art web spam and Spam 2.0 filtering methods to highlight the unresolved issues and open problems, while at the same time effectively capturing the knowledge in the domain of spam filtering.This dissertation proposes three solutions in the area of Spam 2.0 filtering including: (1) characterising and profiling Spam 2.0, (2) Early-Detection based Spam 2.0 Filtering (EDSF) approach, and (3) On-the-Fly Spam 2.0 Filtering (OFSF) approach. All the proposed solutions are tested against real-world datasets and their performance is compared with that of existing Spam 2.0 filtering methods.This work has coined the term ‘Spam 2.0’, provided insight into the nature of Spam 2.0, and proposed filtering mechanisms to address this new and rapidly evolving problem.