Detection of Chinese Deceptive Reviews Based on Pre-Trained Language Model

Abstract

The advancement of the Internet has changed people’s ways of expressing and sharing their views with the world. Moreover, user-generated content has become a primary guide for customer purchasing decisions. Therefore, motivated by commercial interest, some sellers have started manipulating Internet ratings by writing false positive reviews to encourage the sale of their goods and writing false negative reviews to discredit competitors. These reviews are generally referred to as deceptive reviews. Deceptive reviews mislead customers in purchasing goods that are inconsistent with online information and thus obstruct fair competition among businesses. To protect the right of consumers and sellers, an effective method is required to automate the detection of misleading reviews. Previously developed methods of translating text into feature vectors usually fail to interpret polysemous words, which leads to such functions being obstructed. By using dynamic feature vectors, the present study developed several misleading review-detection models for the Chinese language. The developed models were then compared with the standard detection-efficiency models. The deceptive reviews collected from various online forums in Taiwan by previous studies were used to test the models. The results showed that the models proposed in this study can achieve 0.92 in terms of precision, 0.91 in terms of recall, and 0.91 in terms of F1-score. The improvement rate of our proposal is higher than 20%. Accordingly, we prove that our proposal demonstrated improved performance in detecting misleading reviews, and the models based on dynamic feature vectors were capable of more accurately capturing semantic terms than the conventional models based on the static feature vectors, thereby enhancing effectiveness.

Keywords

• natural language processing
• detection of deceptive reviews
• language model
• deep learning
• BERT