T-Bert: A Spam Review Detection Model Combining Group Intelligence and Personalized Sentiment Information

The content of online comments largely affects users’ willingness to purchase goods or services. Driven by interests, spam reviews continue to emerge to induce users maliciously. Most of the existing related work is based on the easy-camouflaged feature information, and the deep learning model is rarely used. The BERT model is prominent in various tasks in the NLP field, and whether it can be successfully applied to the spam review identification task has not been verified. In this paper, we propose a new research strategy for this task: the multi-dimensional representation combining group intelligence and users’ personalized sentiment information can more effectively detect spam reviews. Through fine-grained sentiment analysis of reviews based on product dimension and user dimension, we effectively acquire group intelligence and user personalized sentiment, respectively; Based on the ability of BERT to model the embedding of text context information, the semantic information is acquired. Finally, the three are combined based on Triple Network structure to detect spam reviews. We conduct a large number of experiments on three public datasets and the recall rate and F1 value both exceed the results of state-of-the-art works, which proves the feasibility and effectiveness of our proposed strategy, and verifies the modeling ability of the BERT in the task of detecting spam reviews.