Innovation diffusion has been studied extensively in a variety ofdisciplines, including sociology, economics, marketing, ecology, and computerscience. Traditional literature on innovation diffusion has been dominated bymodels of aggregate behavior and trends. However, the agent-based modeling(ABM) paradigm is gaining popularity as it captures agent heterogeneity andenables fine-grained modeling of interactions mediated by social and geographicnetworks. While most ABM work on innovation diffusion is theoretical,empirically grounded models are increasingly important, particularly in guidingpolicy decisions. We present a critical review of empirically groundedagent-based models of innovation diffusion, developing a categorization of thisresearch based on types of agent models as well as applications. By connectingthe modeling methodologies in the fields of information and innovationdiffusion, we suggest that the maximum likelihood estimation framework widelyused in the former is a promising paradigm for calibration of agent-basedmodels for innovation diffusion. Although many advances have been made tostandardize ABM methodology, we identify four major issues in model calibrationand validation, and suggest potential solutions.
展开▼
