Online reviews significantly influence consumer purchasing decisions, making the detection of deceptive reviews crucial for maintaining the integrity of e-commerce platforms. This paper provides a comprehensive review of the existing literature on deceptive online review detection, synthesizing various approaches and highlighting key research directions. We categorize the existing studies based on their methodologies (linguistic analysis, behavioral analysis, network analysis, and machine learning) and discuss the advantages and limitations of each approach. We identify several gaps in the current research, such as the need for more sophisticated techniques to handle the evolving tactics used by deceptive reviewers and the development of robust methods to assess the impact of deceptive reviews on consumer behavior. Finally, we propose future research directions that focus on interdisciplinary approaches combining different methods, incorporating real-time detection mechanisms, and exploring the ethical and societal implications of deceptive review detection.

Wei Zhang, Qiang Wang, Jian Li, Zhiyong Mai, Guobin Bai, Rong Pan