Decoding deception in the online marketplace: enhancing fake review detection with psycholinguistics and transformer models

Online reviews significantly influence consumer decision-making in digital marketplaces, yet the proliferation of fake reviews threatens their credibility. This study investigates the psycholinguistic features that differentiate human-written fake reviews from genuine ones and explores how these features, along with distributional semantics, can be leveraged for automatic detection. Using a dataset of 3070 reviews from 307 participants, we analyze linguistic patterns with the Linguistic Inquiry and Word Count tool and train machine learning classifiers to predict review authenticity. Our findings reveal distinct psycholinguistic markers in fake reviews, including heightened cognitive processes and emotional exaggeration, and demonstrate the superior performance of transformer-based models like BERT in fake review detection. This research contributes theoretically by linking psycholinguistic cues with advanced natural language processing techniques and offers practical insights for improving review monitoring systems.