气象灾害舆情的时空演化特征及影响因素分析

Analysis of the Spatio-Temporal Evolution Characteristics and Influencing Factors of Public Opinion on Meteorological Disasters

社交媒体有助于气象灾害信息传播扩散,气象灾害舆情的发展会影响公众对灾害的认知以及态度。文章以2021年“‘3·15’沙尘暴”“郑州暴雨”“台风烟花”舆情事件为研究对象,结合LDA(Latent Dirichlet Allocation,隐含狄利克雷分布)主题模型及情感词典分析探讨气象灾害舆情的时间演化特征,并基于空间自相关理论分析舆情热度的空间分布情况及其影响因素。结果表明:不同舆情阶段大众关注的主题显著不同,气象灾害舆情文本中蕴含的平均正向情绪随舆情阶段呈现递增的趋势,平均负向情绪在爆发期时达到峰值;不同地区对气象灾害关注的热度显著不同,其主要受空间距离、地区经济、网民规模等因素的影响。研究结果揭示了气象灾害舆情时空演化的普遍特征,以期为气象灾害舆情的阶段性引导及治理提供理论指导。

Social media contributes to the spread of meteorological disaster information.The development of public opinion on meteorological disasters affects public perceptions of disasters as well as attitudes.This study takes the "3·15 sandstorm","Zhengzhou rainstorm",and "typhoon fireworks" in 2021 as the research objects,and combines LDA Theme Analysis and Sentiment Dictionary Analysis to explore the temporal evolution characteristics of public opinion on meteorological disasters.This study also analyzes the spatial distribution of public opinion hotness in different regions and influencing factors based on spatial autocorrelation theory.The results show that the themes of public concern differ significantly at different stages of public opinion.The average positive sentiment embedded in the public opinion text tends to increase with the stage of public opinion,and the average negative sentiment reaches its peak during the outbreak period.Different regions pay significantly different attention to meteorological disasters,which are mainly influenced by factors such as spatial distance,regional economy,and netizens′ scale.The research results reveal the universal characteristics of public opinion on meteorological disasters,which provide theoretical guidance for the stage guidance and governance of meteorological disaster public opinion.