Detecting Fake Online Reviews: An Unsupervised Detection Method With a Novel Performance Evaluation

ABSTRACT

Fake reviews are critical issues in the online world, as they affect the credibility of e-commerce platforms and undermine consumers’ trust. Therefore, fake-review detection is of great significance. Since fake-review detection is an unsupervised problem, most existing methods and performance metrics cannot be applied. In addition, contemporary review manipulations are much more difficult to detect than before. To address these two problems, we first propose a fully unsupervised method with steps of survey research, fake-review feature analysis, fake index estimation, and fake-review selection. Fake-review features can be accurately derived from existing studies and survey research. Second, we propose a recommendation-based performance metric for evaluating fake-review detection methods. This metric differs from traditional binary classification performance metrics, as it can be used on review data with no objective review authenticity classifications. In this research, we utilize Dianping as a case study to evaluate the effectiveness of the proposed detection method and performance metric.

KEYWORDS AND PHRASES:

• Fake-review detection
• unsupervised problem
• fake reviews
• online recommenders
• recommender metric
• recommender metric
• online reviews

Acknowledgments

This work was supported by the National Natural Science Foundation of China [grants 72101258, 71903189, 72210107001], the 6th Young Elite Scientist Sponsorship Program by CAST [no. YESS20200198], and the Fund for Building World-Class Universities (disciplines) of Renmin University of China [no. KYGJC2023010].

Disclosure statement

No potential conflicts of interest are reported by the authors(s).

Supplemental data

Supplemental data for this article can be accessed online at https://doi.org/10.1080/10864415.2023.2295067

Additional information

Notes on contributors

Yuchen Pan

Yuchen Pan ([email protected]) is an associate professor with tenure in the School of Information Resource Management at Renmin University of China. His research focuses on information sciences, big data analysis and mining, and recommender systems. Dr. Pan has authored or coauthored papers in such journals as Journal of Management Information Systems, Decision Support Systems, International Journal of Production Research, Information Sciences, IEEE Systems Journal, and others.

Lu Xu

Lu Xu ([email protected]; corresponding author) is an associate professor with tenure in the School of Information Resource Management at Renmin University of China. She earned her Ph.D. from Tsinghua University. Dr. Xu’s research interests encompass information sciences, data mining, and financial technology. Her work has been published in such journals as Australia Economics Papers and Economic Research Journal.