Measurement and evolution of government attention to the health industry in China based on the BERTopic model

Objectives: This paper aims to measure the government’s attention to the health industry accurately, which is crucial for understanding policy directions and resource allocation strategies. Methods: Addressing the limitations of traditional word frequency methods, such as restricted word segmentation and ambiguous terms, the BERTopic (Bidirectional Encoder Representations from Transformers Topic Modeling) is applied to measure government attention at the sentence level. Rule matching in an ambiguous dictionary, which is expanded by utilizing the word2vec model, is to achieve accurate identification of unclassified topics. This approach reveals policy concerns at the semantic level. Results: The BERTopic model is a more precise instrument for evaluating the health industry’s attention. Furthermore, significant regional differences are detected. Attention in the Northeast has declined, remained stable in the Central and Western regions, and continuously increased in the Eastern region. The main areas of government attention in the health industry are sports and fitness, environmental governance, medical services, and healthy older individuals’ care. The mode of medical care in healthy retirement has evolved to a combination of medical care and health preservation. Conclusions: It is recommended that the balanced development of the health industry across regions be promoted based on specific local conditions. Efforts should also be made to enhance the efficiency of medical services, optimize the allocation mechanism for medical resources, establish a systematic medical treatment plan, and encourage the comprehensive and coordinated development of the health industry.