Uncover Product Review Patterns via Weighted Motifs

摘要: In today’s e-commercial websites, product reviews written by genuine users are commonly seen, which play a crucial role as customer feedbacks and planting seeds to trigger much more transactions. However, motivated profits, fake crafted spammers inevitable promote or demote reputations whereas misguiding potential buyers make bad decisions. Until recently, the problem how distinguish whether review is fraudulent reviewer spammer has long been studied, but question of general pattern mining still open. this paper, we model online systems into bipartite networks adopt network technique, called weighted motif uncover underlying reviewing patterns. Experiments on Amazon’s dataset show that, our system feasible effective.