Detecting Opinion Spammer Groups Through Community Discovery and Sentiment Analysis

摘要: In this paper we investigate on detection of opinion spammer groups in review systems. Most existing approaches typically build pure content-based classifiers, using various features extracted from contents; however, spammers can superficially alter their contents to avoid detections. our approach, focus user relationships built through interactions identify spammers. Previously, revealed the existence implicit communities among users based upon interaction patterns [3]. work further explore community structures distinguish spam non-spam ones with sentiment analysis interactions. Through extensive experiments over a dataset collected Amazon, found that discovered strong positive are more likely be groups. fact, results show approach is comparable state-of-art classifier, meaning reliably even if contents.