ABSTRACT
With the intensified social conflicts and cyberspace crises, the public is facing the emotional impact and lack of security feelings responding to emergencies. The most recent research only focuses on the influence of discrete emotions, but the induced stressful feeling of emotional security has not been a concern by the government. In this work, we first propose a concept of social-emotional security, evolving from the classical theories of risk society and psychological resilience. Second, we integrate a social-emotional security index measurement method with the proposed three metrics: emotional bias, situational risk, and potential hazard. We also suggest a grading scheme for the emotional regulation strategy with a 0.3 safety valve. Finally, the accuracy is over 78% for detecting the potential risk of emerging events, and the method is feasible in another 30 social safety events with a trend coincidence beyond 63.3%.
ABSTRACT
Health support has been sought by the public from online social media after the outbreak of novel coronavirus disease 2019 (COVID-19). In addition to the physical symptoms caused by the virus, there are adverse impacts on psychological responses. Therefore, precisely capturing the public emotions becomes crucial to providing adequate support. By constructing a domain-specific COVID-19 public health emergency discrete emotion lexicon, we utilized one million COVID-19 theme texts from the Chinese online social platform Weibo to analyze social-emotional volatility. Based on computed emotional valence, we proposed a public emotional perception model that achieves: (1) targeting of public emotion abrupt time points using an LSTM-based attention encoder-decoder (LAED) mechanism for emotional time-series, and (2) backtracking of specific triggered causes of abnormal volatility in a cognitive emotional arousal path. Experimental results prove that our model provides a solid research basis for enhancing social-emotional security outcomes.