SentiBERT: A Novel Approach for Fake Review Detection Incorporating Sentiment Features with Contextual Features
Arvind Mewada, Rupesh Kumar Dewang, Paritosh Goldar, Sushil Kumar Maurya · 2023
Fake (deceptive) reviews have become a serious problem for online consumers, with the proliferation of online marketplaces leading to an increase in spurious reviews that are often used to lure or discourage potential customers. While sentiment analysis has been introduced to the e-commerce sector, the lack of an effective method to differentiate between authentic and fake reviews is still a major challenge. Existing approaches face issues such as slow convergence and inadequate precision. In order to address these challenges, this paper proposes a new approach that integrates sentiment features into the review detection process. The proposed approach uses a feature extraction method that utilizes a preconstructed sentiment dictionary, a pre-trained BERT model to extract feature vectors, and a fully connected dense layer to classify reviews as real or fake using the softMax function. The effectiveness of the proposed approach was evaluated on the Yelp dataset, showing a nearly 7% improvement in accuracy compared to existing feature sets and a nearly 4% improvement over existing state-of-the-art methods. The integration of sentiment features has shown promising results in detecting fake reviews, which is crucial for ensuring a fair and trustworthy online marketplace.