Inferring and Simulating Human Behaviors for Societal Decision-Making

Attend this academic lecture exploring the intersection of artificial intelligence and human behavior modeling for societal decision-making. Learn about two key approaches to understanding human behaviors when direct observation is challenging: inferring behaviors from novel data sources and simulating behaviors using generative AI. Discover how researchers infer hourly mobility networks from aggregated location data and model COVID-19 spread to inform pandemic policies. Explore recent advances in using generative AI models to simulate diverse human behaviors, including public opinions, social networks, and mobility trajectories. Gain insights into how fine-grained behavioral understanding can support high-stakes societal decisions, particularly in public health contexts where traditional observation methods face cost, privacy, or feasibility constraints. The presentation covers both theoretical foundations and practical applications of AI-driven behavioral modeling, demonstrating how computational approaches can address critical challenges in understanding and predicting human behavior patterns for policy development and societal benefit.