Understand Public Perspectives about “Industrial worker health” Based on Weibo Data : Content Analysis and Topic Modeling Study

Abstract Background Promoting the construction of a healthy China is a national strategy to comprehensively enhance the health quality of the Chinese nation and achieve coordinated development between people’s health and the economy and society. Strengthening safety production and occupational health work, improving working conditions, and enhancing the health quality of industrial workers are important aspects of building a healthy China. However, there is currently a lack of research on the content of speeches on online platforms such as Sina Weibo. Objective This study used a web crawler approach to obtain people’s opinions about “Industrial worker health”.We investigated the value of Chinese social media and related public perceptions and response. The goal was to determine if this data is suitable for public response.Through this exploration, the paper seeks to provide evidence-based recommendations to enhance the alignment of digital public opinion with the overarching goals of the “Healthy China” strategy, ultimately promoting the health and welfare of the industrial workforce. Methods This paper employed cutting-edge web scraping techniques to harvest data from the prominent social media platform, Sina Weibo. Through the application of sophisticated data collection tools, specifically the “Houyi Collector”, the study focuses on the keyword “industrial workers' health” to extract relevant information from Sina Weibo, thereby capturing the pulse of online discussions regarding the health concerns and awareness of industrial laborers.The gathered dataset is then meticulously analyzed using the Latent Dirichlet Allocation (LDA) topic modeling technique to identify and categorize the principal themes and trends that prevail in the online conversations. This analytic approach is intended to uncover the breadth and trajectory of public attention and attitudes toward the well-being of industrial workers within the context of the “Healthy China” initiative. Results By illuminating the digital footprint of health-related industrial worker discourses on a major Chinese social media platform, this research contributes a nuanced understanding of the virtual labor community’s engagement with health issues. Conclusions The insights derived from the LDA topic modeling are set to inform stakeholders, including policymakers, health advocates, and industrial enterprises, regarding the focal points and sentiments that shape the online narrative on industrial workers’ health in China.