Spatial-Temporal Pattern Evolution of Public Sentiment Responses to the COVID-19 Pandemic in Small Cities of China: A Case Study Based on Social Media Data Analysis

The impact of the COVID-19 pandemic on public mental health has become increasingly prominent. Therefore, it is of great value to study the spatial-temporal characteristics of public sentiment responses to COVID-19 exposure to improve urban anti-pandemic decision-making and public health resilience. However, the majority of recent studies have focused on the macro scale or large cities, and there is a relative lack of adequate research on the small-city scale in China. To address this lack of research, we conducted a case study of Shaoxing city, proposed a spatial-based pandemic-cognition-sentiment (PCS) conceptual model, and collected microblog check-in data and information on the spatial-temporal trajectory of cases before and after a wave of the COVID-19 pandemic. The natural language algorithm of dictionary-based sentiment analysis (DSA) was used to calculate public sentiment strength. Additionally, local Moran's I, kernel-density analysis, Getis-Ord Gi* and standard deviation ellipse methods were applied to analyze the nonlinear evolution and clustering characteristics of public sentiment spatial-temporal patterns at the small-city scale concerning the pandemic. The results reveal that (1) the characteristics of pandemic spread show contagion diffusion at the micro level and hierarchical diffusion at the macro level, (2) the pandemic has a depressive effect on public sentiment in the center of the outbreak, and (3) the pandemic has a nonlinear gradient negative impact on mood in the surrounding areas. These findings could help propose targeted pandemic prevention policies applying spatial intervention to improve residents' mental health resilience in response to future pandemics.