ARCHIVES

Abstract: Fake reviews are intentionally misleading or deceptive online evaluations of products or services that are written by individuals or organizations with the intention of manipulating the perception of the item being reviewed. These fake reviews can have significant consequences for businesses and consumers alike. The detection of fake reviews is therefore an important problem that has garnered significant attention from researchers in various fields. In this review, we examine the current state of the art in fake review detection methods, and identify a range of approaches and techniques that have been developed to automatically identify fake reviews. We also discuss the limitations and challenges of current fake review detection methods, and suggest directions for future research to improve the accuracy and robustness of these techniques. Key Word: Fake reviews, review fraud, review manipulation, review spam, machine learning, natural language processing, content analysis, crowd-sourced annotation, sales data. References [1] X. Feng, Y. Zhang, J. Liu, and M. Li, "A survey on fake review detection: Techniques, datasets, and tools," in Proceedings of the 25th International Conference on World Wide Web, pp. 1477-1478, 2016. [2] [2] H. Li, B. Liu, A. Mukherjee , J. Shao, and Y. Liu, "Spotting fake reviews using positive-unlabeled learning," in Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 2329-2338, 2018. [3] B. Liu, Y. Liu, M. Li, and X. Su, "Identifying fake hotel reviews," in Proceedings of the 22nd ACM International Conference on Information and Knowledge Management, pp. 1295-1304, 2013. [4] J. Jadhav and D. Parasar, "Fake review detection system through analytics of sales data," in Proceedings of the 3rd International Conference on Cloud Computing, Data Science & Engineering (Confluence), pp. 791-796, 2018. [5] Y. Hu, J. Cheng, and B. Liu, "Fake review detection for online hotel booking," in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 33013309, 2017. [6] J. Liu, Y. Liu, M. Li, and X. Su, "Identifying fake reviews using temporal patterns," in Proceedings of the 25th International Conference on World Wide Web, pp. 1479-1480, 2016. [7] Q. Wang, X. Feng, J. Liu, and M. Li, "Identifying fake reviews using tree-based learning algorithms," in Proceedings of the 26th International Conference on World Wide Web, pp. 1461-1470, 2017. [8] Y. Liu, J. Liu, M. Li, and X. Su, "Identifying fake reviews using graphbased features," in Proceedings of the 24th ACM International Conference on Information and Knowledge Management, pp. 169178, 2015. [9] H. Xu, B. Liu, M. Li, and X. Su, "A survey on fake review detection," ACM Computing Surveys, vol. 53, no. 4, pp. 1-38, 2020.