Detecting Spam Reviews for Improving House Sharing Recommendation

Abstract

With the rapid development of technology, the business model of the tourism industry has changed. More and more people need to rent the houses, and it is easier for customers to use and get information on the Internet. In the era of Web 2.0, consumers can leave rating scores and write reviews on the online social platforms to share their experience with others. Nonetheless, there may exist some spam reviews. In this paper, we propose a novel approach to detect user profiles and spam reviews so as to generate a rental house recommendation. With this new mechanism, consumers can receive an appropriate recommendation from their own basic information, preference, and their close friends or family who are with powerful influence on them. Also, with the support of the proposed mechanism, less fake or useless reviews influence them.