Detecting Review Spam on Amazon with ReviewAlarm

When making purchasing decisions, customers increasingly rely on opinions posted on the Internet. Businesses therefore have an incentive to promote their own products or demote competitors’ products by creating positive or negative spam reviews on platforms like Amazon.com. Several researchers propose methods and tools to detect review spam automatically. Reviewskeptic is an automated tool developed by Ott et al (2012) which attempts to identify spam reviews on hotels by employing text-related criteria. This research proposes a framework for detecting also non-hotel spam reviews with reviewskeptic by enhancing the tool with reviewer behavior related and time related criteria derived from the literature. The new framework will be called ReviewAlarm. A ground of truth dataset has been created by the means of a manual assessment and has been used to compare the performance of reviewskeptic and ReviewAlarm on this dataset. With ReviewAlarm we are able to improve the performance of the tool on our dataset. However, this research also reveals several weaknesses about the criteria that are being used in review spam detection. Therefore, we argue that additional qualitative research related to reviewer behavior and the criteria is needed in order to come up with better tools and more generalizable criteria.