Temporal Dynamics of Emotions during the COVID-19 Pandemic at the Center of Outbreak: A Sentimental Analysis of Weibo Tweets from Wuhan.

2021 
BACKGROUND The ongoing COVID-19 pandemic increased the general public's anxiety, depression, post-traumatic stress disorder (PTSD), and psychological stress in various degrees worldwide. Better tailored mental health services and interventions cannot be achieved until we understand the patterns of mental health issues after disasters, especially in the rapid transmission of the COVID-19. Understanding the public's emotions and needs and their distribution attributes are critical for making appropriate public policies and eventually respond to the disasters effectively, efficiently, and equitably. OBJECTIVE This study aims to detect the temporal patterns of emotional fluctuation, the significant events that affected the emotional changes and variations, and the hourly variations of the emotions within a day. METHODS Based on a longitudinal dataset of 816,556 posts tweeted by 27,912 Weibo users in Wuhan from December 31, 2019, to April 31, 2020, we processed general sentiment inclination rating and the type of sentiments of Weibo tweets by Pandas and SnowNLP Python libraries. We also grouped the hours into five time groups to measure the netizens' sentimental changes during different periods in a day. RESULTS Overall, negative emotions like surprise, fear, and anger are the salient emotions on the social media platform. Milestone events, such as the confirmation of human-to-human transmission, are the primary events that ignited the emotions. Emotions varied within a day. Although all emotions are more prevalent in the afternoon and night, fear and anger are more dominant in the morning and afternoon, while depression is more salient during the night. CONCLUSIONS Milestone events during the pandemic are the primary events that ignited the citizens' emotions. In addition, the emotions varied within a day. Better-tailored mental health services and interventions could be conducted accordingly. CLINICALTRIAL
    • Correction
    • Source
    • Cite
    • Save
    • Machine Reading By IdeaReader
    43
    References
    3
    Citations
    NaN
    KQI
    []