A network-based approach to detect spammer groups

Online reviews nowadays are an important source of information for consumers to evaluate online services and products before deciding which product and which provider to choose. Therefore, online reviews have significant power to influence consumers' purchase decisions. Being aware of this, an increasing number of companies have organized spammer review campaigns, in order to promote their products and gain an advantage over their competitors by manipulating and misleading consumers. To make sure the Internet remains a reliable source of information, we propose a method to identify both individual and group spamming reviews by assigning a suspicion score to each user. The proposed method is a network-based approach combining clustering techniques. We demonstrate the efficiency and effectiveness of our approach on a real-world and manipulated dataset that contains over 8000 restaurants and 600,000 restaurant reviews from TripAdvisor website. We tested our method in three testing scenarios. The method was able to detect all spammers in two testing scenarios, however it did not detect all in the last scenario.