Authors: Qingxi Peng
Tags: 2013, conceptual modeling
Reviews and comments play important role in online shopping. It can help people getting more information about stores and products. The potential customers tend to make decision according to it. However, driven by profit and fame, spammers post spurious reviews to mislead the customers by promoting or demoting target store. Previous studies mainly focused on the text features and ratings to identify fake reviews. However, these studies ignore the importance of relationship between store and reviewer. This paper first proposes sentiment analysis techniques to calculate the sentiment score of reviews. Then a relationship-based method has been proposed to identify the spammers. We also present an algorithm which can detect both single-mode spammers and multi-mode spammers. A subset of highly suspicious reviewers is selected for evaluation by human judges. Experimental results show that the proposed method can find out the review spammer efficiently.Read the full paper here: https://link.springer.com/chapter/10.1007/978-3-319-14139-8_30
