Artificial Intelligence-Powered Social Network Analytics for Urban Health Intelligence: A Data-Driven Approach to Public Health Surveillance and Intervention

Abstract

Urban populations, characterized by high density and intricate mobility patterns, are highly susceptible to disease transmission at a fast pace. The understanding of disease transmission due to human contact in such areas is required for proper public health intervention. This paper takes into account the application of artificial intelligence (AI) and social network analysis (SNA) for predicting disease transmission dynamics within urban settings. We base our work on data from anonymized mobile phone tracing, public health surveillance, and social media metrics, using machine learning and graph modeling—i.e., graph neural networks and temporal network analysis—to monitor and predict the trends in disease transmission. Preliminary findings are that AI-enabled SNA models outperform traditional epidemiology tools in predicting transmission hubs and high-risk individuals or populations. The results indicate the potential of artificial intelligence-powered social network analysis as a valuable real-time monitoring device and targeted intervention device for urban health governance.