Dynamic Insights: Unraveling Public Demand Evolution in Health Emergencies Through Integrated Language Models and Spatial-Temporal Analysis

Abstract

Background and Purpose: In public health emergencies, rapid perception and analysis of public demands are essential prerequisites for effective crisis communication. Public demands serve as the most instinctive response to the current state of a public health crisis. Therefore, the government must promptly grasp and leverage public demands information to enhance the effectiveness and efficiency of health emergency management, that is planned to better deal with the outbreak and meet the medical demands of the public. Methods: This study employs dynamic topic mining and knowledge graph construction to analyze public demands, presenting a spatial-temporal evolution analysis method for emergencies based on EBU models. EBU models are three large language models, including ERNIE, BERTopic, and UIE. Results: The data analysis of Shanghai's city closure and control during the COVID-19 epidemic has verified that this method can simplify the labeling and training process, and can use massive social media data to quickly, comprehensively, and accurately analyze public demands from both time and space dimensions. From the visual analysis, geographic information on public demands can be quickly obtained and areas with serious problems can be located. The classification of geographical information can help guide the formulation and implementation of government policies at different levels, and provide a basis for health emergency material dispatch. Conclusion: This study extends the scope and depth of research on health emergency management, enriching subject categories and research methods in the context of public health emergencies. The use of social media data underscores its potential as a valuable tool for analyzing public demands. The method can provide rapid decision supports for decision-making for public services such as government departments, centers for disease control, medical emergency centers and transport authorities.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 6 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.