Fake reviews detection based on LDA

It is necessary for potential consume to make decision based on online reviews. However, its usefulness brings forth a curse - deceptive opinion spam. The deceptive opinion spam mislead potential customers and organizations reshaping their businesses and prevent opinion-mining techniques from reaching accurate conclusions. Thus, the detection of fake reviews has become more and more fervent. In this work, we attempt to find out how to distinguish between fake reviews and non-fake reviews by using linguistic features in terms of Yelp Filter Dataset. To our surprise, the linguistic features performed well. Further, we proposed a method to extract features based on Latent Dirichlet Allocation. The result of experiment proved that the method is effective.