Opinion Fraud Detection via Neural Autoencoder Decision Forest
This addresses the issue of misleading fake reviews for online shoppers, but it is incremental as it builds on existing techniques.
The paper tackled the problem of detecting fake online reviews by proposing a unified model combining autoencoder and random forest, which outperformed existing methods on a large Amazon review dataset.
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.