Semi-Supervised Learning Based Fake Review Detection

The impact of product reviews on the business platform is growing, giving consumers more information about their products and directly influencing consumers' buying decisions. However, the existence of fake reviews makes the consumer cannot make the right judgments of sellers, which can also causes the credibility of the platform downgraded. Thus, it is of practical significance to identify the fake reviews in the platform. The way of manually annotating the data set is difficult, meanwhile it is nearly impossible to make the correct annotation by reading only a small portion of comments based on the classifier trained under the traditional method. In previous studies, it has been shown that false comments have characteristics such as high similarity in content and high concentration of comments. In this paper, we propose a new algorithm to identify fake reviews based on semi-supervised learning method. Real data based experiments have demonstrated that the proposed method can achieve desired performance.