欢迎访问《图学学报》 分享到：
图学学报

图学学报 ›› 2021, Vol. 42 ›› Issue (2): 222-229.DOI: 10.11996/JG.j.2095-302X.2021020222

• 计算机图形学与虚拟现实 • 上一篇    下一篇

基于情感特征的新冠肺炎疫情舆情演化分析

  

  1. 1. 郑州联大教育集团，河南 郑州 450001；  2. 郑州大学软件学院，河南 郑州 450002； 3. 河南师范大学软件学院，河南 新乡 453007；  4. 郑州大学信息工程学院，河南 郑州 450001
  • 出版日期:2021-04-30 发布日期:2021-04-30
  • 基金资助:
    国家自然科学基金项目(6160051017)；国家重点研发计划项目；河南省高等学校青年骨干教师培养计划

Public opinion evolution analysis of “COVID-19 epidemic” based on sentiment feature 

  1. 1. Zhengzhou United Education Group, Zhengzhou Henan 450001, China;  2. School of Software, Zhengzhou University, Zhengzhou Henan 450002, China;  3. College of Software, Henan Normal University, Xinxiang Henan 453007, China;  4. School of Information Engineering, Zhengzhou University, Zhengzhou Henan 450001, China
  • Online:2021-04-30 Published:2021-04-30
  • Supported by:
    National Natural Science Foundation of China (6160051017); National Key R & D Plan; Plan for Young Backbone Teachers in Henan Province 

PDF (PC)

96

摘要： 针对突发事件的舆情演变态势进行分析，发现社会舆情的演变规律，提出了一种基于情感特征的 舆情演化分析方法，该方法包含舆论情感分析模块与舆情演化分析模块。舆论情感分析模块基于 BERT 预训练模 型和 BiGRU 模型，其中 BERT 作为词嵌入模型提取舆情文本特征向量，BiGRU 则用于提取文本特征向量的上下 文联系实现对舆情数据情感极性的精准判别。在舆情演化分析模块中，将舆情的情感特征在时间维度上进行动态 可视化建模，并基于其结果实现舆情数据的演化规律解析。在实验部分，利用 2020 年 1 月 1 日到 2020 年 2 月 19 日的 100 万条新冠肺炎背景下的舆论数据进行了数值实验，实验结果表明，该方法能够有效地对疫情背景下的舆 情数据进行演化分析。

关键词: 新冠肺炎, 舆情情感分析, 舆情演变分析

Abstract:  In order to analyze the evolution of public opinion under emergencies and discover the law of the evolution of public opinion, a sentiment feature-based public opinion evolution analysis method was proposed, includdinga News Sentiment Analysis Module and a Public Opinion Evolution Analysis Module. The News Sentiment Analysis Module was based on the BERT pre-training model and the BiGRU model, where BERT was extracted as a word embedding, and BiGRU was employed to extract the contextual links of the textual feature vector to achieve a better understanding of the sentiment polarity of public opinion data. In the Public Opinion Evolution Analysis Module, this paper modeled the dynamic visualization of the sentiment features of public opinion in the time dimension, and then based on the visualization results, enabled the resolution of evolutionary patterns of public opinion data. Finally, a numerical experiment was conducted using one million pieces of the COVID-19 news data from January 1, 2020 to February 19, 2020. The experimental results show that the method proposed in this paper can effectively analyze the sentiment polarity of public opinion data. 

Key words:  , COVID-19, analysis of public sentiment and emotion, analysis of public opinion evolution

中图分类号: