Search

• We employ statistical analysis to define a list of quality features. • We propose a joint model by fusing autoencoder and random forest in an end-to-end trainable way for fake review detection. • Experimental results on the real dataset demonstrate the efficiency of the model. Online reviews play an important role in influencing buyers' daily purchase decisions. However, fake and meaningless reviews, which cannot reflect users' genuine purchase experience and opinions, widely exist on the Web and pose great challenges for users to make right choices. Therefore, it is desirable to build a fair model that evaluates the quality of products by distinguishing spamming reviews. We present an end-to-end trainable unified model to leverage the appealing properties from Autoencoder and random forest. A stochastic decision tree model is implemented to guide the global parameter learning process. Extensive experiments were conducted on a large Amazon review dataset. The proposed model consistently outperforms a series of compared methods. [ABSTRACT FROM AUTHOR]