Understanding the impact of emotional support on mental health resilience of the community in the social media in Covid-19 pandemic

Background: Emotional support in social media can act as a buffer against the negative impact of affective disorders. However, empirical evidence relating to emotional support in social media and how it influences the wider public remains scanty. The objective of this study is therefore to conduct a prototype investigation into the translation mechanism of emotional support in social media, providing empirical evidence for practitioners to use to tackle mental health issues for the wider public. Methods: A regression model is proposed to examine the relationship between perceived and received emotional support. Received emotional support is set as the dependent variable and measured using public activity. Perceived emotional support is derived using Natural Language Processing (NLP)-based content analysis. The model is then analyzed using a panel date with a total number of 61,297 posts from 17 Weibo accounts in 17 provincial administrative units in China. Results: The relationship between perceived and received emotional support is not linear but complex, suggesting that translation of emotional support is not automatic. Further, our empirical evidence suggests that the translation of emotional support in social media is affected by frequency and pandemic stage. Limitations: The study does not examine the direct relationship between perceived and received emotional support, instead adopting public activity as a proxy for the latter construct. In addition, the relationship between perceived and received emotional support is more complex than linear, requiring further model and theory development.