People share their consumption experience and opinions to product as online product reviews or word-of-mouths. Consumers consult the product reviews posted by other consumers before making purchase decision. As a result, the influence of online product reviews increase dramatically. Since the influence of product reviews increase, firms may commit to improve product quality to earn positive opinions. Nevertheless, some firms choose the shortcut by hiring people to write positive fake reviews to promote themselves, as well as write negative fake reviews to demote product of their competitors. The fake product reviews may influent or even manipulate the majority of public opinion. However, fake reviewers always hide the real identities of themselves. Audiences have no idea about who are spammers. This paper analyzes a real case of fake reviews in Taiwan by social network techniques. To our knowledge, few previous studies had use social network techniques to detect fake reviewer. Thus, we propose a novel method of using social network analysis indices as features to detect spammer. The relationship of authors of product reviews posts and their replies might be used for spammer group detection.
Proceedings of the 2016 IEEE 17th International Conference on Information Reuse and Integration (IEEE IRI 2016)