Fake Online Reviews on Digital Platforms: Conceptual Boundaries, Detection Methods and Trustworthy Governance

Xingying Feng; Rui Wang; Jiaming Lu

doi:10.54097/zshkn702

Authors

Xingying Feng
Rui Wang
Jiaming Lu

DOI:

https://doi.org/10.54097/zshkn702

Keywords:

Fake Review, Online Review, Deceptive Opinion Spam, Feature Engineering, Detection Method, Explainable Artificial Intelligence

Abstract

Digital evaluation has become one of the necessary contents of the market information system, but the same way that it addresses information asymmetry may also give people reasons to distort their reputations. Gather the results of the 64 investigations on forged web feedback from the survey, and then, based on conceptual boundaries, obvious signs, identification systems and reliable applications, classify them. According to the assessment, there are now disputes over what should be regarded as fake reviews; at the same time, data collection, attribute accuracy and algorithm benchmarks have also been subject to debate. Linguistic patterns are still used in the first stage of screening at the review stage, but now reliable detection is more often based on reviewer patterns, chronological spikes and collaborative dynamics due to the systematic nature of deception in platform engagement architecture. Supervised, unsupervised and semi-supervised methods should be considered different ways to apply various works, not a hierarchy of efficiency. Interpretability is also being used in the regulatory process to connect the results of algorithms with human review, appeals and changes in policy and corporate social responsibility, etc. Based on the above, this paper will introduce a general architecture for object demarcation, deception patterns, visible traits, identification structure and explanatory oversight. Next, we will carry out boundary-aware collection, construct an adaptable cross-website model, perform implementation-oriented evaluation and human-centric management.

Downloads

Download data is not yet available.

References

[1] Park, D.-H., & Lee, J. (2008). eWOM overload and its effect on consumer behavioral intention depending on consumer involvement. Electronic Commerce Research and Applications, 7(4), 386–398. https://doi.org/10.1016/j.elerap.2007.11.004. DOI: https://doi.org/10.1016/j.elerap.2007.11.004

[2] Pocchiari, M., Proserpio, D., & Dover, Y. (2023). Online reviews: A literature review and roadmap for future research. SSRN Electronic Journal. https://doi.org/10. 2139/ssrn. 456 5563. DOI: https://doi.org/10.2139/ssrn.4565563

[3] Luca, M., & Zervas, G. (2013). Fake it till you make it: Reputation, competition, and Yelp review fraud. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2293164. DOI: https://doi.org/10.2139/ssrn.2293164

[4] Zhang, W., Wang, Q., Ma, Z., Li, J., & Xie, R. (2022). Research on the publishing motivation and formation mechanism of online commodity fake reviews. Chinese Journal of Management Science, 30(7), 176–188. (In Chinese). https://doi.org/10.16381/j.cnki.issn1003-207x.2019.2022.

[5] Xylogiannopoulos, K. F., Xanthopoulos, P., Karampelas, P., & Bakamitsos, G. A. (2024). ChatGPT paraphrased product reviews can confuse consumers and undermine their trust in genuine reviews. Can you tell the difference? Information Processing & Management, 61(6), 103842. https://doi.org/10. 1016/j. ipm.2024.103842. DOI: https://doi.org/10.1016/j.ipm.2024.103842

[6] Mohawesh, R., Xu, S., Tran, S. N., Ollington, R., Springer, M., Jararweh, Y., et al. (2021). Fake reviews detection: A survey. IEEE Access, 9, 65771–65802. https://doi.org/10. 1109/access. 2021. 3075573. DOI: https://doi.org/10.1109/ACCESS.2021.3075573

[7] Gupta, R., Jindal, V., & Kashyap, I. (2024). Recent state-of-the-art of fake review detection: A comprehensive review. The Knowledge Engineering Review, 39. https://doi.org/ 10.1017/ s0269888924000067. DOI: https://doi.org/10.1017/S0269888924000067

[8] Song, X., & Sun, X. (2015). A review of consumer online review adoption research. Journal of Modern Information, 35(1), 164–169. (In Chinese). https://doi.org/10. 3969/j.issn. 1008-0821.2015.01.032.

[9] Jindal, N., & Liu, B. (2007). Review spam detection. In Proceedings of the 16th International Conference on World Wide Web (pp. 1189–1190). https://doi.org/10.1145/ 1242572. 1242759. DOI: https://doi.org/10.1145/1242572.1242759

[10] Jindal, N., & Liu, B. (2008). Opinion spam and analysis. In Proceedings of the International Conference on Web Search and Web Data Mining - WSDM '08 (p. 219). https://doi. org/10. 1145/ 1341531.1341560. DOI: https://doi.org/10.1145/1341531.1341560

[11] Ott, M., Choi, Y., Cardie, C., & Hancock, J. T. (2011). Finding deceptive opinion spam by any stretch of the imagination. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (pp. 309–319).

[12] Bozkurt, S., Welch, E., Gligor, D., Gligor, N., Garg, V., & Pillai, K. G. (2023). Unpacking the experience of individuals engaging in incentivized false (and genuine) positive reviews: The impact on brand satisfaction. Journal of Business Research, 165, 114077. https://doi.org/10.1016/j.jbusres.2023.114077. DOI: https://doi.org/10.1016/j.jbusres.2023.114077

[13] Li, J., Ott, M., Cardie, C., & Hovy, E. (2014). Towards a general rule for identifying deceptive opinion spam. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (pp. 1566–1576). https://doi.org/10.3115/v1/P14-1147. DOI: https://doi.org/10.3115/v1/P14-1147

[14] Li, C., Xiang, J., & Xiang, J. (2019). A credibility evaluation method for online product reviews. Journal of Computer Applications, 39(1), 181–185. (In Chinese). https://doi.org/10. 11772/ j.issn. 1001-9081.2018051154.

[15] Wang, C., He, C., & Wang, K. (2015). Perceived usefulness of follow-up reviews in online word-of-mouth. Management Science, 28(3), 102–114. (In Chinese). https://doi. org/10. 3969/j. issn.1672-0334.2015.03.009.

[16] Zheng, J., & Duan, Y. (2022). The influence of follow-up reviews on consumers' purchase intention on e-commerce platforms: Evidence from Taobao. Business Economics Research, (13), 80–84. (In Chinese).

[17] Rayana, S., & Akoglu, L. (2015). Collective opinion spam detection. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 985–994). https://doi.org/10.1145/ 2783258. 2783 370. DOI: https://doi.org/10.1145/2783258.2783370

[18] Kumar, A., Gopal, R. D., Shankar, R., & Tan, K. H. (2022). Fraudulent review detection model focusing on emotional expressions and explicit aspects: investigating the potential of feature engineering. Decision Support Systems, 155, 113728. https://doi.org/10.1016/j.dss.2021.113728. DOI: https://doi.org/10.1016/j.dss.2021.113728

[19] Yang, C. (2019). Fake review detection based on review text content and reviewer behavior features [Master’s thesis]. Shanghai Normal University. (In Chinese).

[20] Mukherjee, A., Liu, B., & Glance, N. (2012). Spotting fake reviewer groups in consumer reviews. In Proceedings of the 21st International Conference on World Wide Web (pp. 191–200). https://doi.org/10.1145/2187836.2187863. DOI: https://doi.org/10.1145/2187836.2187863

[21] Fei, G., Mukherjee, A., Liu, B., Hsu, M., Castellanos, M., & Ghosh, R. (2013). Exploiting burstiness in reviews for review spammer detection. Proceedings of the International AAAI Conference on Web and Social Media, 7(1), 175–184. https://doi.org/10.1609/icwsm.v7i1.14400. DOI: https://doi.org/10.1609/icwsm.v7i1.14400

[22] Wu, X., Dong, Y., Tao, J., Huang, C., & Chawla, N. V. (2017). Reliable fake review detection via modeling temporal and behavioral patterns. In 2017 IEEE International Conference on Big Data (Big Data) (pp. 494–499). https://doi.org/10.1109/ bigdata. 2017.8257963. DOI: https://doi.org/10.1109/BigData.2017.8257963

[23] Heydari, A., Tavakoli, M., & Salim, N. (2016). Detection of fake opinions using time series. Expert Systems with Applications, 58, 83–92. https://doi.org/10.1016/j. eswa.2016. 03. 020. DOI: https://doi.org/10.1016/j.eswa.2016.03.020

[24] Li, F., Huang, M., Yang, Y., & Zhu, X. (2013). Learning to identify review spam. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence (pp. 2488–2493). https://doi.org/10.5591/978-1-57735-516-8/IJC AI11-414.

[25] Yan, M., Ji, D., & Ren, Y. (2019). Fake review identification based on a hierarchical attention neural network model. Journal of Computer Applications, 39(7), 1925–1930. (In Chinese). https://doi.org/10.11772/j.issn.1001-9081. 2018 112 340.

[26] Du, S., Yang, M., & Qiu, R. (2023). Online product fake review identification based on SMOTE-RF and multidimensional feature vectors. Journal of Intelligence, 42(4), 156–164. (In Chinese). https://doi.org/10.3969/j.issn.1002-1965.2023. 04. 022.

[27] Song, H., Yan, X., Yu, Z., Shi, L., & Su, F. (2013). Fake review detection based on adaptive clustering. Journal of Nanjing University (Natural Sciences), 49(4), 433–439. (In Chinese). https://doi.org/10.13232/j.cnki.jnju.2013.04.005.

[28] Wang, G., Xie, S., Liu, B., & Yu, P. S. (2011). Review graph based online store review spammer detection. In 2011 IEEE 11th International Conference on Data Mining (pp. 1242–1247). https://doi.org/10.1109/icdm.2011.124. DOI: https://doi.org/10.1109/ICDM.2011.124

[29] Lin, Y., Zhu, T., Wang, X., Zhang, J., & Zhou, A. (2014). Towards online review spam detection. In Proceedings of the 23rd International Conference on World Wide Web (pp. 341–342). https://doi.org/10.1145/2567948.2577293. DOI: https://doi.org/10.1145/2567948.2577293

[30] Mothukuri, R., Aasritha, A., Krishna Chaitanya, M., Kesava Nandini, P., & Gopi Krishna, P. (2022). Fake Review Detection using Unsupervised Learning. In 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS) (pp. 119–125). https://doi. org/ 10. 1109/icscds53736.2022.9760908. DOI: https://doi.org/10.1109/ICSCDS53736.2022.9760908

[31] Ren, Y., Ji, D., & Yin, L. (2014). Research on deceptive review identification based on semi-supervised learning algorithms. Journal of Sichuan University (Engineering Science Edition), 46(3), 62–69. (In Chinese). https://doi.org/10. 15961/j. jsuese. 2014.03.022.

[32] Zhang, W., Wang, Q., Bu, C., Li, J., & Zhang, S. (2020). Online fake review identification based on co-training. Systems Engineering - Theory & Practice, 40(10), 2669–2683. (In Chinese). https://doi.org/10.12011/1000-6788-2019-1089-15.

[33] Ren, Y., Ji, D., Zhang, H., & Yin, L. (2015). Research on deceptive review identification based on PU learning. Journal of Computer Research and Development, 52(3), 639–648. (In Chinese). https://doi.org/10.7544/issn1000-1239.2015. 201 31473.

[34] Yin, C., & Zhu, Y. (2020). A fake review detection model based on vertical ensemble Tri-training. Journal of Computer Applications, 40(8), 2194–2201. (In Chinese). https://doi.org/ 10. 11772/ j.issn.1001-9081.2019112046.

[35] Chen, J.-Y., & Wang, Y.-J. (2022). Semi-Supervised Fake Reviews Detection based on AspamGAN. Journal of Artificial Intelligence and Capsule Networks, 4(1), 17–36. https:// doi. org/ 10.36548/jaicn.2022.1.002. DOI: https://doi.org/10.36548/jaicn.2022.1.002

[36] Wu, Z., Liu, G., Wu, J., & Tan, Y. (2022). Are neighbors alike? A semi-supervised probabilistic ensemble for online review spammers detection. SSRN Electronic Journal. https://doi.org/ 10.2139/ ssrn.4013130. DOI: https://doi.org/10.2139/ssrn.4013130

[37] Mukherjee, A., Venkataraman, V., Liu, B., & Glance, N. (2013). What Yelp fake review filter might be doing?. Proceedings of the International AAAI Conference on Web and Social Media, 7(1), 409–418. https://doi.org/ 10.1609/ icwsm. v7i1.14389. DOI: https://doi.org/10.1609/icwsm.v7i1.14389

[38] Hermosilla, P., Berríos, S., & Allende-Cid, H. (2025). Explainable AI for forensic analysis: A comparative study of SHAP and LIME in intrusion detection models. Applied Sciences, 15(13), 7329. https://doi.org/10.3390/app15137329 DOI: https://doi.org/10.3390/app15137329

[39] AlZeyadi, H., Sert, R., & Duran, F. (2025). A lightweight, explainable spam detection system with Rüppell's Fox Optimizer for the social media network X. Electronics, 14(21), 4153. https://doi.org/10.3390/electronics14214153. DOI: https://doi.org/10.3390/electronics14214153

[40] Praveen Goud, V., & Morusupalli, R. (2025). SHAP for explainable feature engineering and LIME-based interpretability to enhance fake profile detection. In Lecture Notes in Computer Science (pp. 152–163). https://doi.org/ 10. 1007/ 978-981-95-4963-4_13. DOI: https://doi.org/10.1007/978-981-95-4963-4_13