Detecting Fake Reviews Based on Review-Rating Consistency and Multi-dimensional Time Series

摘要

Online reviews can help people get more information about stores and products. The potential customers tend to make decisions according to them. However, driven by profit, spammers post fake reviews to mislead the customers by promoting or demoting target store. Previous studies mainly utilize the rating as an indicator for detection. However, these studies ignore an important problem that the rating cannot represent the sentiment accurately. In this paper, we propose a method of identifying fake reviews based on rating- review consistency and multi-dimensional time series. We first incorporate the sentiment analysis techniques into fake review detection. Then, we further discuss the relationship between ratings and fake reviews. In the end, this paper establishes an effective time series to detect fake reviews. Experimental results show that our proposed methods have good detection result and outperform state-of-art methods.