BERT-based deceptive review detection in social media: introducing DeceptiveBERT

In recent years, the Internet has facilitated the emergence of social media platforms as significant channels for individuals to express their thoughts and engage in instantaneous interactions. However, the reliance on online reviews has also given rise to deceptive practices, where anonymous spammers generate fake reviews to manipulate the perception of a product. Ensuring the integrity of the online review system requires identifying and mitigating fake reviews. While existing machine learning (ML)- and neural network (NN)-based sentiment analysis methods can detect deceptive reviews, they often suffer from long training times, high computational resource requirements, and memory constraints. This study aims to overcome these limitations by introducing a transformer-based “deceptive bidirectional encoder representations from transformers (DeceptiveBERT) model.” This model utilizes contextual representations to enhance the precision of deceptive review identification. Transfer learning is employed to leverage knowledge from a pre-existing BERT base-uncased word embedding model, enabling efficient feature extraction. The proposed model incorporates a combination of classification layers to categorize reviews into two distinct categories: deceptive and truthful. Additionally, the study addresses the challenge of imbalanced datasets by utilizing three separate datasets and implementing appropriate methodologies for dataset curation. The effectiveness of the DeceptiveBERT model was evaluated through experimentation. The results demonstrate its efficacy, with the model achieving accuracy rates of 75%, 84.79%, and 81.08% on the Ott, YelpNYC, and YelpZip datasets, respectively.