A framework for computing crowd emotions using agent based modeling

We present a computational framework for modeling geospatial dynamics of crowd emotions as part of anticipatory analysis. The framework is based on agent based modeling (ABM) and evaluation-activation space for emotion representation. ABM is a simulation technique that uses the actions and interactions of individual agents to represent the behavior of a given population or system. The agent based models used in this paper employ geospatial data such as elevation, population density and locations of interest to define the context of agent decisions. We apply our framework to model the emotional dynamic of a population during disaster evacuation. In our examples we use a simple evacuation scenario: the agents learn of an incoming hurricane and evacuate for safety to the nearest shelter. At each time step, an agent chooses the direction of motion using a bounded rationality model that accounts for his or her emotional state (an evaluation-activation tuple) and geospatial context. After t time steps we use fuzzy set methods to analyze the crowd emotions in each of the N_s shelters.