Toward a Theoretically Grounded Framework for Digital Epidemiological Enquiry: Integrating Behavioral Models, Information Diffusion, and AI-Driven Infoveillance Using a COVID-19 Vaccine Case Study

I.A. Kashim

PDF

Section

Research Articles

Issue

Volume 2 Issue 1 (2026): In Progress

How to Cite

Kashim, I. (2025). Toward a Theoretically Grounded Framework for Digital Epidemiological Enquiry: Integrating Behavioral Models, Information Diffusion, and AI-Driven Infoveillance Using a COVID-19 Vaccine Case Study. Crisis and Resilience, 2(1), 8-17. https://journals.explorerpress.com/index.php/cr/article/view/55

Authors

I.A. Kashim

Faculty of Public Health, Texila American University/ Central University of Nicaragua

Abstract

Digital epidemiology has emerged as a critical complement to traditional surveillance by leveraging digitally generated data to monitor population health behaviors and perceptions in near real time. Despite rapid methodological advances, the field remains dominated by tool-centric approaches, with limited integration of behavioral theory capable of explaining how information exposure translates into health-related decision-making. This article advances a theory-building, analytically grounded framework for digital epidemiological enquiry and empirically illustrates its application using a COVID-19 vaccine discourse case study from the United Kingdom and the United States. Drawing on the Health Belief Model (HBM), infodemiology, and information diffusion theory, the framework links perceived susceptibility, severity, benefits, barriers, and cues to action with AI-enabled sentiment and topic analytics. Using a large corpus of vaccine-related Twitter data, natural language processing and topic modeling were employed to operationalize behavioral constructs in digital discourse. Findings demonstrate that sentiment and thematic patterns can approximate key behavioral dimensions, while also revealing important limitations related to structural context, trust, and collective narratives that are only partially visible in digital traces. The study contributes a theoretically informed, empirically grounded approach for advancing digital epidemiology as an explanatory and policy-relevant discipline.

Keywords:

Digital epidemiology, Infodemiology, Health Belief Model, sentiment analysis, topic modeling, social media, COVID-19 vaccination

References

[1]Eysenbach, G. (2009). Infodemiology and infoveillance: Framework for an emerging set of public health informatics methods. Journal of Medical Internet Research, 11(1), Article e11. https://doi.org/10.2196/jmir.1023.

[2]Salathé, M., Bengtsson, L., Bodnar, T. J., Brewer, D. D., Brownstein, J. S., Buckee, C., ... & Brownstein, J. S. (2012). Digital epidemiology. PLOS Computational Biology, 8(7), Article e1002616. https://doi.org/10.1371/journal.pcbi.1002616.

[3]Eysenbach, G. (2020). How to fight an infodemic: The four pillars of infodemic management. Journal of Medical Internet Research, 22(6), Article e21820. https://doi.org/10.2196/21820.

[4]Cinelli, M., Quattrociocchi, W., Galeazzi, A., Valensise, C. M., Schmidt, A. L., Zollo, F., & Scala, A. (2020). The COVID-19 social media infodemic. Scientific Reports, 10, Article 16598. https://doi.org/10.1038/s41598-020-73510-4.

[5]Hussain, S., Tahir, M., Hussain, H., Sheikh, T., Dashtipour, A., & Naseem, T. M. (2021). Artificial intelligence–enabled analysis of public attitudes toward COVID-19 vaccines in the United Kingdom and the United States. Journal of Medical Internet Research, 23(4), Article e26627. https://doi.org/10.2196/26627.

[6]Kashim, I. A. (2025). A review of public perceptions of COVID-19 vaccination on social media using sentiment analysis [Doctoral dissertation, Texila American University / Central University of Nicaragua].

[7]Rosenstock, I. M. (1974). Historical origins of the Health Belief Model. Health Education Monographs, 2(4), 328–335. https://doi.org/10.1177/109019817400200403.

[8]Glanz, K., Rimer, B. K., & Viswanath, K. (2015). Health behavior: Theory, research, and practice (5th ed.). Jossey-Bass.

[9]Rogers, E. M. (2003). Diffusion of innovations (5th ed.). Free Press.

[10]Hutto, C. J., & Gilbert, E. (2014). VADER: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of the International AAAI Conference on Web and Social Media, 8(1), 216-225.

[11]Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3, 993–1022.

[12]Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. (2016). The rise of social bots. Communications of the ACM, 59(7), 96–104. https://doi.org/10.1145/2818717.

[13]Hancock, J. T., Naaman, A., & Levy, M. (2020). AI-mediated communication. Proceedings of the National Academy of Sciences, 117(51), 31794–31802. https://doi.org/10.1073/pnas.2013275117.

[14]Lazer, D. M. J., Baum, M. A., Benkler, Y., Berinsky, A. J., Greenhill, K. M., Menczer, F., ... & Zittrain, J. L. (2018). The science of fake news. Science, 359(6380), 1094–1096. https://doi.org/10.1126/science.aao2998.

[15]Floridi, L., & Cowls, J. (2020). A unified framework of five principles for AI in society. Harvard Data Science Review, 2(1). https://doi.org/10.1162/99608f92.8cd550d1.

This work is licensed under a Creative Commons Attribution 4.0 International License.

Article Sidebar