A normative agent-based model for predicting smoking cessation trends

Norms are an important part of human social systems, governing many aspects of group decision-making. Yet many popularly used social models neglect to model normative effects on human behavior, relying on simple probabilistic and majority voting models of influence diffusion. Within the multi-agent research community, the study of norm emergence, compliance, and adoption has resulted in new architectures and standards for normative agents; however few of these models have been successfully applied to real-world public policy problems. In this paper, we propose a new lightweight architecture for constructing normative agents to model human social systems; the aim of our research is to be able to study the effects of different public policy decisions on a community. Here we present a case study showing the usage of our architecture for predicting trends in smoking cessation resulting from a smoke-free campus initiative. Our agent-based model combines social, environmental, and personal factors to accurately predict smoking trends and attitudes. The performance of both the whole and ablated model is evaluated against statistics from an independent source.