基于文本数据的灾害信息风险监测与预警集成方法研究  

An Integrated Method for Risk Monitoring and Early Warning of Disaster Information Based on Text Data

作　　者：王治莹[1] 陈笑 刘翰界 WANG Zhiying;CHEN Xiao;LIU Hanjie(School of Management Science and Engineering,Anhui University of Technology,Ma’anshan 243032,China)

机构地区：[1]安徽工业大学管理科学与工程学院,安徽马鞍山243032

出　　处：《灾害学》2024年第4期81-87,共7页Journal of Catastrophology

基　　金：国家自然科学基金项目“行为决策视角下多种舆情信息异步演化及其多阶段干预决策研究”(72074002);国家自然科学基金项目“多种诱导信息情境下突发公共事件舆情演进规律及其干预机制研究”(71704001);安徽省自然科学基金项目“重大突发事件舆情危机演化规律与干预决策”(2208085Y20);安徽省高校杰出青年基金项目“考虑舆情态势的重大突发事件应急决策方法”(2022AH020031)。

摘　　要：基于灾害信息的文本数据,该文提出一种风险监测与预警集成方法,以提高灾害信息风险监测效率及监测支持预警的针对性。首先,运用八爪鱼数据采集器采集和处理灾害信息的文本数据;其次,运用BTM主题模型构建灾害信息风险监测模型,得到主题热度趋势并确定具有高风险且亟待预警的话题;然后,提出灾害信息风险预警指标体系和预警等级判定方法,计算所确定话题的风险综合指标预警加权值,并结合预警区间判定预警等级;最后,以2021年“7·20”郑州特大暴雨灾害信息的风险监测和预警为例进行实验分析,验证所提方法的可行性。研究表明,该方法可将灾害信息的文本数据贯穿于风险监测与预警两个过程,有助于为监测结果更有针对性地支持预警工作提供参考。Based on text data related to disaster information,an integrated method for risk monitoring and early warning is proposed to improve the efficiency of disaster information risk monitoring and the targeted support for early warning provided by monitoring.First,the Octopus data collector is used to collect and process the text data.Second,the BTM topic model is used to construct a risk monitoring model to get topic heat trends and identify high-risk topics requiring urgent warnings.Then,a risk early warning indicator system and a method for determining early warning levels are proposed to calculate the weighted value of the risk integrated early warning indicator for the identified topics and determine early warning levels based on early warning intervals.Finally,the risk monitoring and early warning of the“7·20”Zhengzhou heavy rainstorm disaster information in 2021 is taken as an example for experimental analysis to verify the feasibility of the proposed method.The study shows that this method can integrate the text data of disaster information into both the risk monitoring and early warning processes,providing valuable insights into how monitoring results can be better targeted to support early warning efforts.

关 键 词：灾害信息 风险监测 风险预警 集成方法 文本数据 BTM主题模型 

分 类 号：X43[环境科学与工程—灾害防治] X915.5[天文地球—大气科学及气象学] P49