Toward Modeling Emotional Crowds

Abstract

This paper presents an Emotion Network structure for modeling crowd emotions to simulate socially emotional crowds. The emotion model focuses on entire crowds, builds individual emotion spaces as network nodes, embodies psychological linkages with relationship arcs, and clusters emotionally homogeneous crowds into EmotionTrees. According to the maximum value of the emotion component and the psychological distance, crowds are initialized as different trees. With relational distributions of crowd changes, agents move between different subgroups. Then, we construct emotion-oriented commands with subgroup constraints according to intergroup emotion theory. For execution, motion variables are calculated from emotion commands (i.e., emotion source-oriented orientation, and velocity and emotion strength-based motion clip selection). Experiments on bystanders, football fans, violent protestors, and guided marching behaviors demonstrate that the Emotion Network can improve crowd behavior modeling with particular attention to the impacts of group constraints and emotional characteristics, which can reflect environment stimuli and changes. The model can be integrated into physical crowd simulators as a high-level emotion manager, providing intelligent emotional support in improving the realism of human-like crowds.