WIZER: A Tool for Automating Model Improvement in Multi-Agent Social- Network Systems

There has been a significant increase in the use of multi-agent social-network models due to their ability to flexibly model emergent behaviors in complex sociotechnical systems while linking to real data. These models are growing in size and complexity which requires significant time and effort for calibration, validation, model-improvement, and to gain understanding as to why the models behave as they do. In this paper, we present our knowledge-based simulation-aided approach for automating model-improvement and WIZER, our tool implementing this approach. WIZER is capable of calibrating and validating multi-agent social-network models, and facilitates model-improvement and understanding. By employing knowledge-based search, causal analysis, and simulation control and inference techniques, WIZER can reduce the number of simulation runs needed to calibrate, validate, and improve a model and improve the focus of these runs. We ran a preliminary version of WIZER on BioWar – a city-scale social agent network simulation of the effects of weaponized biological attacks on a demographically-realistic population within a background of naturally-occurring diseases. The results demonstrate the efficacy of WIZER.