Learning to Generate Diverse and Authentic Reviews via an Encoder-Decoder Model with Transformer and GRU
Kaifu Jin, Xi Zhang, Jiayuan Zhang · 2019
Fake reviews automatically generated by machine learning models can be manipulated to influence the customers opinions, which is a great threat to online review platforms like social networks and E-commerce websites. Previous review generation methods generally adopt either businesses information (e.g. location and products) or existing review texts from consumers as inputs, while currently no approach that utilizes both types of information has been reported. As business information can help generated reviews gain relevance, and existing user reviews help improve the diversity of generated reviews, we envision that an integration of these two types of information is likely to result in a better review generator. To this end, we propose an encoder-decoder model to produce authentic and diverse reviews, which applies Transformer and mutative Gated Recurrent Unit (GRU) to encode the business information and the customer reviews, respectively. In addition, to address the lack of suitable metrics for evaluating the diversity of reviews, we developed a novel text diversity metric called DMet. Our experiments on Yelp dataset demonstrate that the model we developed can produce reviews with better quality and diversity as compared to existing methods, and DMet is able to closely match human judgment in evaluating text diversity.