Computerized Textual Analysis of Fake News

The global proliferation of fake news is commanding widespread attention and exerting a profound impact on our society. To stem the tide of fake content on social media platforms, we need intervention strategies that can operate at scale. These strategies, such as content labeling, must be grounded in computational models capable of evaluating information content in real time.

In addition, other applications like robo-advising in FinTech and online product reviews, which rely on the integrity of information, can greatly benefit from robust machine learning methods designed to detect and filter out fake content.

My research addresses this pressing need by utilizing computerized textual analysis to explore three critical dimensions of fake news: detection methods, societal impacts, and mitigation strategies. Through this research, I hope to offer valuable insights and practical tools to counter the damaging effects of fake news in our increasingly digital world.

Related publications:

• Ng, K. C., Ke, P. F., So, M. K. P., and Tam, K. Y. 2023. “Augmenting Fake Content Detection in Online Platforms: A Domain Adaptive Transfer Learning via Adversarial Training Approach,” Production and Operations
Management. (32:7), pp. 2101–2022.

• Ng, K. C., Tang, J., and Lee, D. 2021. “The Effect of Platform Intervention Policies on Fake News Dissemination and Survival: An Empirical Examination,” Journal of Management Information Systems (38:4), pp. 898–930.

• Tang, J., and Ng, K. C. 2019. “Reposts Influencing the Effectiveness of Social Reporting System: An Empirical Study from Sina Weibo,” ICIS 2019 Proceedings.13.