Product reviews have been the focus of numerous research efforts. In particular, the problem of identifying fake reviews has recently attracted significant interest. Writing fake reviews is a form of attack, performed to purposefully harm or boost an item's reputation. The effective identification of such reviews is a fundamental problem that affects the performance of virtually every application based on review corpora. While recent work has explored different aspects of the problem, no effort has been done to view the problem from the attacker's perspective. In this work, we perform an analysis that emulates an actual attack on a real review corpus. We discuss different attack strategies, as well as the various contributing factors that determine the attack's impact. These factors determine, among others, the authenticity of fake review, evaluated based on its linguistic features and its ability to blend in with the rest of the corpus. Our analysis and experimental evaluation provide interesting findings on the nature of fake reviews and the vulnerability of online review-corpora.
展开▼
