Public Attitudes Towards Violence Against Doctors: Sentiment Analysis of Chinese Users (Preprint)

Abstract

Violence against doctors attracts the public’s attention both online and in the real world. Understanding the change in public opinion is essential to monitor public sentiment and make strategies to comfort the public’s emotions.

This study aims to quantify the difference in public sentiment according to online public opinion life cycle theory and describe an evolution of public sentiment during a high-profile violence against doctors’ crisis in China.

This study used the term frequency-inverse document frequency (TF-IDF) algorithm to extract key terms and created keyword clouds from textual comments. The Latent Dirichlet Allocation (LDA) topic model was employed to analyze the thematic evolution within public sentiment. The integrated Chinese Sentiment Lexicon was used to analyze the evolution of sentiments in the collected data.

12,775 valid comments were collected on public opinion on Sina Weibo in China. Thematic and sentiment analyses showed that the public’s sentiments were highly negative during the outbreak period (Disgust: 33.52%, Anger: 22.32%), then smoothly changed to positive and negative during the spread period (Sorrow: 34.45%, Joy: 32.46%), and tended to be rational and peaceful during the decline period (Joy: 32.71%, Sorrow: 27.98%). However, no matter how emotions change, the leading tone of each period contains a large number of negative sentiments.

This study simultaneously examined the dynamics of theme change and sentiment evolution in crises involving violence against doctors. It discovered that public sentiment varied in tandem with the theme shifts, yet the dominant sentiment from the initial stage of public opinion prevailed throughout. This finding, distinguished from prior research, underscored the enduring impact of initial public sentiment. The results offered valuable insights for medical institutions and authorities, suggesting the need for tailored risk communication strategies responsive to the evolving themes and sentiments at different stages of a crisis.