Affiliation:
1. School of Information Management, Nanjing University, Nanjing, China
Abstract
Objective The COVID-19 pandemic has spurred an increased interest in online healthcare and a surge in usage of online healthcare platforms, leading to a proliferation of user-generated online physician reviews. Yet, distinguishing between genuine and fake reviews poses a significant challenge. This study aims to address the challenges delineated above by developing a reliable and effective fake review detection model leveraging deep learning approaches based on a fake review dataset tailored to the context of Chinese online medical platforms. Methods Inspired by prior research, this paper adopts a crowdsourcing approach to assemble the fake review dataset for Chinese online medical platforms. To develop the fake review detection models, classical machine learning models, along with deep learning models such as Convolutional Neural Network and Bidirectional Encoder Representations from Transformers, were applied. Results Our experimental deep learning model exhibited superior performance in identifying fake reviews on online medical platforms, achieving a precision of 98.36% and an F2-Score of 97.97%. Compared to the traditional machine learning models (i.e., logistic regression, support vector machine, random forest, ridge regression), this represents an 8.16% enhancement in precision and a 7.7% increase in F2-Score. Conclusion Overall, this study provides a valuable contribution toward the development of an effective fake physician review detection model for online medical platforms.
Funder
National Natural Science Foundation of China
Reference70 articles.
1. Fox S, Duggan M. Health Online 2013, https://www.pewresearch.org/internet/2013/01/15/health-online-2013/ (2013, accessed 23 October 2023).
2. Silver L, Huang C. In Emerging Economies, Smartphone and Social Media Users Have Broader Social Networks, https://www.pewresearch.org/internet/2019/08/22/in-emerging-economies-smartphone-and-social-media-users-have-broader-social-networks/ (2019, accessed 23 October 2023).
3. Improving the effectiveness of online healthcare platforms: An empirical study with multi-period patient-doctor consultation data
4. Wu G, Greene D, Smyth B, et al. Distortion as a validation criterion in the identification of suspicious reviews. In: Proceedings of the First Workshop on Social Media Analytics, Washington D.C., District of Columbia, USA, 25–28 July 2010, pp.10–13. New York: ACM.
5. Mukherjee A, Venkataraman V, Liu B, et al. What yelp fake review filter might be doing? In: Proceedings of the 7th International Conference on Weblogs and Social Media, Massachusetts, USA, 8–11 July 2013, pp.409–418. Menlo Park: AAAI.