图书情报工作 ›› 2022, Vol. 66 ›› Issue (11): 87-99.DOI: 10.13266/j.issn.0252-3116.2022.11.010

• 情报研究 • 上一篇    下一篇

会话分析视角下的突发公共事件主题演化研究——以"新冠肺炎疫情"为例

翟姗姗, 王左戎, 陈欢, 潘港辉   

  1. 华中师范大学信息管理学院 武汉 430079
  • 收稿日期:2021-10-29 修回日期:2022-01-17 出版日期:2022-06-05 发布日期:2022-06-18
  • 作者简介:翟姗姗,副教授,博士,E-mail:zhais@mail.ccnu.edu.cn;王左戎,硕士研究生;陈欢,硕士研究生;潘港辉,硕士研究生。
  • 基金资助:
    本文系国家社会科学基金青年项目"大数据视角下突发公共卫生事件信息协同体系研究"(项目编号:20CTQ021)研究成果之一。

Research on Topic evolution of Public Emergencies from the Perspective of Conversation Analysis:A Case Study of COVID-19

Zhai Shanshan, Wang Zuorong, Chen Huan, Pan Ganghui   

  1. School of Information Management, Central China Normal University, Wuhan 430079
  • Received:2021-10-29 Revised:2022-01-17 Online:2022-06-05 Published:2022-06-18

摘要: [目的/意义] 会话分析理论的引入为主题演化研究提供了新的研究视角,细化了主题演化分析粒度。同时,更为完善的主题演化分析思路被应用于突发公共事件之中,有利于提升监管部门的舆情疏导效率。[方法/过程] 针对现有研究中的主题识别方法与主题演化判断标准,结合会话分析与主题分析,将会话内容与会话组织结构引入主题演化分析过程中,并以"新冠肺炎疫情"中用户生成内容(UGC)作为数据来源进行实证分析。通过基于时序性与讨论热度的主题演化分析,从主题强度层面识别不同层级内容的演化规律,并在主题内容分析层面引入知识发现的关联规则计算思想以挖掘语料内容间的参照关系,结合社会网络分析方法确定关键演化路径。[结果/结论] 研究结果表明,网络结构中不同层级的主题内容存在一定差异并对主题演化趋势有着重要影响,对有着重要作用的层级的内容进行有效监管会对引导舆情走向产生积极作用。

关键词: 会话分析, 突发公共事件, 主题识别, 主题演化, 关联规则

Abstract: [Purpose/Significance] The introduction of conversation analysis theory provides a new research perspective for the study of topic evolution and refines the granularity of topic evolution analysis. At the same time, a more perfect theme evolution analysis approach is applied to public emergencies, which is conducive to improving the efficiency of public opinion guidance of regulatory departments. [Method/Process] Based on the topic identification methods and topic evolution judgment criteria in existing studies, this paper combined conversation analysis and topic analysis to introduce conversation contents and conversation organization structure into the process of topic evolution analysis, and used user-generated content in COVID-19 as data source for empirical analysis. Through the topic evolution analysis based on temporal sequence and discussion hot, the evolution laws of contents at different levels were identified from the topic intensity level. The association rule calculation idea of knowledge discovery was introduced at the topic content analysis level, to mine the reference relationship between corpus contents, and the key evolution path was determined by combining the social network analysis method. [Result/Conclusion] The results show that there are certain differences in the topic contents at different levels in the network structure and it has an important influence on the evolution trend of the topic, effective supervision of the contents at important levels will play a positive role in guiding the trend of public opinion.

Key words: conversational analysis, public emergency, topic identification, topic evolution, association rules

中图分类号: