Efficient CPS model based online opinion governance modeling and evaluation for emergency accidents

In the last decades, there have been much more public crisis accidents in the world such as H1N1, H7N9 and Ebola outbreak. It has been proved that our world has come into the time while public crisis accidents number was growing fast. Furthermore, crisis response to these public emergency accidents is always involved in a complex system consisting of cyber, physics and society domains (CPS Model). In order to collect and analyze these emergency accidents with higher efficiency, we need to design and adopt some new tools and models to analysis the online opinion. In this paper, we have proposed a new CPS Model based Online Opinion Governance system which constructed on cellphone APP for data collection including GIS information and online opinion and decision making in the back end. Our contributions include the graded risk classification method and accident classification method. Besides, we propose the group opinion polarization analysis method consisting two models and make promotion of the relative conditional entropy based context key word extraction method. Basing on these, we have built an efficient CPS Model based simulated emergency accident replying and handling system. It has been proved useful for emergency response in some real accidents in China such as Tianjin Explode accident and Haiyan Typhoon in recent years with detailed and vivid analysis result.