A dual-phase framework for detecting authentic and computer-generated customer reviews using large language models

Customer reviews are crucial in potential buyers’ decision-making process. However, on online platforms, the credibility of these reviews is often undermined by fake reviews, which can mislead users. With advancements in large language models (LLMs), the review landscape has transformed, making it more common to encounter computer-generated reviews created using state-of-the-art language models rather than genuine user feedback. This evolution poses significant challenges in distinguishing authentic reviews from artificially generated ones. To address these challenges, we propose a novel dual-phase framework that first generates high-diversity synthetic reviews using advanced LLMs to learn their patterns, and then it leverages this knowledge to enhance fake reviews detection. Our methodology involves two key phases. In the first phase, we generate computer-generated reviews by leveraging advanced methods, including generative transformers, trained on genuine user reviews. In the second phase; traditional and deep learning based classifiers, are incorporated as detection models which classify reviews as either authentic or computer-generated. Evaluated on a benchmark Amazon review dataset, our framework demonstrate (1) the efficacy of our approach in generating diverse and contextually relevant human-based and computerized-based reviews and (2) the robustness of our system in classifying and verifying the authenticity of reviews.