Research on the dynamic mechanism of group emotional expression in the crisis

Abstract

Emotions are considered as an important driving force for the evolution of online public opinion especially in the crisis. However, previous studies on public emotions in the crisis usually focused on the classification, communication, and influence factors of emotions, while omitting the dynamic system of group emotional expression. In this study, we calculate the emotional tendency based on Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis (SKEP). The emotional time series are constructed and the stationarity and randomness of the series are investigated. The largest Lyapunov exponent is employed to analyze the chaos of the emotional time series. The major findings suggest that the phenomenon of public opinion is a process system from the perspective of cybernetics, and the expression of group emotions is a continuous process of this system. The expression of group emotions presents various characteristics at different periods. The emotional time series of the initial period is generated by a stochastic system. Then a chaotic system dominates the group emotional expression in the outbreak period. In the chronic period, the expression process is dominated by a stable non-chaotic system. This study provides a new perspective for the research on the evolution of public opinion, solving the confusion about the concepts of object and process. The findings of this study can help the emergency management departments understand the dynamic mechanism of group emotional expression in the crisis, and provide theoretical support for the guidance and decision-making in emergency response.