摘要
【目的/意义】本文通过探究社交媒体主题分布特征及其在不同情感倾向的差异性,对发掘用户意见表达的特征规律,进而在突发事件风险沟通中制定科学合理的内容发布和情感引导策略,提升风险沟通管理效果具有重要作用。【方法/过程】研究从发文和用户两个维度出发,设计主题分布指标,刻画社交媒体主题的散布状态。采用方差分析,检验主题分布特征在情感倾向上的显著差异,解析影响主题情感演变的内在因素。【结果/结论】实验以新浪微博中高影响力用户的常态发文为样本数据,分析发现:①通过聚焦主题和集中输出观点,可以培养用户在特定领域中的影响力。②高影响力用户习惯于表达明确的情感倾向,且其情感随着时间推移变化。③主题分布热度和广度在发文的积极与消极情感倾向上具有显著差异,且均不受时间因素的影响。【创新/局限】本文构建了主题分布特征分析框架,并探讨了主题分布特征与情感倾向的差异,研究结论可为制定科学的风险沟通策略提供参考。后续可通过探究基于用户常态发文与事件发文的异同规律实现观点和情感预测,辅助突发事件中的舆情风险治理。
【Purpose/significance】By exploring the distribution characteristics of social media topics and their differences in different sentiment,this paper explores the characteristics and laws contained in the expression of opinions of social media users.The research helps formulate scientific content release and emotional guidance strategy,which can improve the effectiveness of risk communication management in emergency.【Method/process】Based on the two dimensions of publication and users,this study designed topic distribution indicators to describe the dispersion state of social media topics.Analysis of variance was used to test the significant difference of topic distribution characteristics in affective tendency,figure out the internal factors affecting the evolution of theme emotion.【Result/conclusion】The experiment uses the daily posts of high-influence users on Sina Weibo as sample data,and the analysis found that:(1)By focused opinion output,users cultivate their influence in specific fields.(2)High-influence users tend to express clear emotion in their posts and the emotion evolutes over time.(3)The topic distribution popularity and breadth have significant differences in the positive and negative sentiment of posts,and are not affected by time factors.【Innovation/limitation】This paper proposes a framework of topic distribution characteristics and discusses the differences between topic distribution and emotional tendencies.The research conclusions can provide references for formulating scientific risk communication strategies.In the future,prediction of opinions and emotion in a specific emergency can be realized by exploring the similarities and differences between users'regular publication and emergency-related publication.Thereby,assisting public opinion risk management in emergencies.
作者
王晓
董迪迪
陈思菁
操玉杰
WANG Xiao;DONG Didi;CHEN Sijing;CAO Yujie(School of Information Management,Central China Normal University,Wuhan 430079,China;Faculty of Artificial Intelligence Education,Central China Normal University,Wuhan 430079,China)
出处
《情报科学》
CSSCI
北大核心
2023年第11期62-71,共10页
Information Science
基金
国家社科基金青年项目“面向风险治理的突发事件事理图谱构建研究”(21CTQ014)。
关键词
主题分布
情感特征
风险沟通
高影响力用户
方差分析
社交媒体
topic distribution
sentiment characteristic
risk communication
high-influence users
analysis of variance
social media
