JMIR Publications

ABSTRACT

Background:

Starting in October 2023, China experienced successive outbreaks and the spread of Influenza A (H3N2). During this period, Sina Weibo (SW) users sought emotional stability and psychological resilience by sharing information and expressing personal opinions. The content generated by users, including text posts, can be analyzed to reveal fluctuations in their emotions and psychological dynamics, thereby providing a valuable reference for assessing their mental health status.

Objective:

This study aims to understand the evolution of emotions expressed on social media during various phases of Influenza A. 

Methods:

We employed the BERT-LSTM model to classify emotions in relevant posts from September 2023 to April 2024 and to correlate these emotions with objective influenza rates.

Results:

The positivity rate of influenza A exhibited an initial upward trend followed by a decline, reaching its peak between November and February of the subsequent year. During this period, the predominant emotional response among the public was one of sadness, which was closely correlated with the fluctuations in the influenza positivity rate. Notably, sadness persisted for some time even after the positivity rate decreased, highlighting the profound impact of influenza on individuals’ psychological well-being and its long-term emotional repercussions. In contrast, the sentiment of surprise fluctuated minimally throughout the observation period, indicating that the public did not experience significant shock or unexpected emotional reactions to the developments related to the flu. As the flu progressed, the public’s emotional responses evolved. In the early stages of the influenza outbreak, neutral emotions diminished due to the predominance of negative emotions such as sadness, fear, and anger. However, neutral sentiment later rebounded and stabilized at a high level, suggesting that the public regained a sense of rationality and emotional equilibrium during the peak of the flu. Additionally, happiness initially declined in the early stages of the flu due to the overshadowing presence of negative emotions, but it gradually increased as the holiday season approached. Overall, the emotional landscape shifted from being predominantly negative in the early stages to a coexistence of positive, negative, and neutral emotions. This evolution in emotional dynamics is closely linked to the adaptability of public psychology, the effectiveness of government control measures and information dissemination, as well as external factors such as festivals and large-scale population movements.

Conclusions:

Conclusion: The phenomenon of social sharing of emotions offers theoretical insights into the collective expression of emotions on social media and the reciprocal influence among individuals. The findings not only provide a fresh perspective on the mechanisms of emotional transmission during public health events but also furnish empirical evidence to guide public opinion and emotional management in the context of Influenza A. Clinical Trial: None