图书情报工作 ›› 2021, Vol. 65 ›› Issue (5): 98-109.DOI: 10.13266/j.issn.0252-3116.2021.05.010

• 情报研究 • 上一篇    下一篇

社交媒体环境下突发事件严重性评估和预警机制研究

安璐1,2, 陈苗苗2, 李纲1   

  1. 1. 武汉大学信息资源研究中心 武汉 430072;
    2. 武汉大学信息管理学院 武汉 430072
  • 收稿日期:2020-09-07 修回日期:2020-11-27 出版日期:2021-03-05 发布日期:2021-04-14
  • 作者简介:安璐(ORCID:0000-0002-5408-7135),教授,博士生导师,E-mail:anlu97@163.com;陈苗苗(ORCID:0000-0002-8384-6452),硕士研究生;李纲(ORCID:0000-0001-5573-6400),教授,博士生导师。
  • 基金资助:
    本文系教育部哲学社会科学研究重大课题攻关项目"提高反恐怖主义情报信息工作能力对策研究"(项目编号:17JZD034)和国家自然科学基金重大课题"国家安全大数据综合信息集成与分析方法"(项目编号:71790612)研究成果之一。

Emergency Severity Assessment and Early Warning Mechanism in the Social Media Environment

An Lu1,2, Chen Miaomiao2, Li Gang1   

  1. 1 Center for Studies of Information Resources, Wuhan University, Wuhan 430072;
    2 School of Information Management, Wuhan University, Wuhan 430072
  • Received:2020-09-07 Revised:2020-11-27 Online:2021-03-05 Published:2021-04-14

摘要: [目的/意义] 突发事件的快速蔓延与恶化使得应急管理部门需实时评估突发事件的严重性,并建立科学的预警机制。微博等社交媒体平台为突发事件的实时研判提供了丰富的线索。[方法/过程] 从网民作用、网媒作用、事态扩散、态度倾向、网民情感等维度构建突发事件严重性评估指标,提出突发事件严重性指标的影响倾向分析及特征比较方法。以2018年“8·24乐清女孩乘车遇害案”“5·6郑州空姐打车遇害案”“8·27昆山持刀砍人案”和2017年“携程亲子园虐童事件”这4个社会安全事件的1 107 308条微博数据为例,通过突发事件严重性指标的影响倾向分析,划分突发事件严重性等级,建立突发事件预警机制。[结果/结论] 研究结果建立了突发事件的量化分级标准,为政府及时采取应急管理措施提供方法指引与数据支持。

关键词: 严重性评估, 预警机制, 突发事件, 社交媒体, 影响力倾向

Abstract: [Purpose/significance] Due to the rapid spread and deterioration of public emergencies, emergency management departments need to evaluate the severity of emergencies in real time and establish a scientific early warning mechanism. Microblogging and other social media platforms provide rich clues for the real-time study and judgment of emergencies. [Method/process] This study constructed the severity assessment indexes of emergencies from the dimensions of the netizens’ role, the Internet media’s role, the spread of events, attitudes and feelings of netizens. The methods of analyzing the influence tendency of the emergency severity indexes and comparing the features were put forward. A total of 1 107 308 microblogging entries regarding four social security incidents of "8.24 Yueqing Girl Riding Murder" "5.6 Zhengzhou Stewardess Taxi Murder" "8.27 Kunshan Knife-Cutting Case" in 2018 and "Ctrip Kindergarten Abuse Incident" in 2017 were investigated. [Result/conclusion] The results of the study establish a quantitative classification standard for public emergencies, and provide method guidance and data support for the governments to take emergency management measures in time.

Key words: severity assessment, early warning mechanism, public emergency, social media, influence tendency

中图分类号: