作者: Gal A. Kaminka , Natalie Fridman
DOI:
关键词: Machine learning 、 Cognitive model 、 Task (project management) 、 Computer science 、 Artificial intelligence 、 Crowd psychology 、 Social comparison theory
摘要: Models of crowd behavior facilitate analysis and prediction human group behavior, where people are affected by each other's presence. Unfortunately, existing models leave many open challenges. In particular, psychology often offer only qualitative description, while computer science simplistic, not reusable from one simulated phenomenon to the next. We propose a novel model based on Festinger's Social Companson Theory (SCT). concrete algorithmic framework for SCT evaluate its implementation in several scenarios. Results task measures judges evaluation shows that produces improved results compared base literature.