基于 RNN-LSTM 新冠肺炎疫情下的微博舆情分析

吉林大学学报(信息科学版) ›› 2022, Vol. 40 ›› Issue (4): 581-588.

基于 RNN-LSTM 新冠肺炎疫情下的微博舆情分析

任伟建^a,b, 刘圆圆^a, 计妍^a , 康朝海^a,b

东北石油大学 a. 电气信息工程学院; b. 黑龙江省网络化与智能控制重点实验室, 黑龙江大庆 163318

收稿日期:2021-11-23 出版日期:2022-08-16 发布日期:2022-08-17
作者简介:任伟建(1963— ), 女, 黑龙江泰来人, 东北石油大学教授, 博士生导师, 主要从事油气集输过程故障诊断研究, (Tel) 86-13845901386(E-mail)renwj@126.com。
基金资助:
国家自然科学基金资助项目(61933007; 61873058)

Public Opinion Analysis on Weibo Based on RNN-LSTM in COVID-19

REN Weijian^a,b, LIU Yuanyuan^a, JI Yan^a , KANG Chaohai ^a,b

a. School of Electrical Information and Engineering; b. Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control, Daqing 163318, China

Received:2021-11-23 Online:2022-08-16 Published:2022-08-17

摘要/Abstract

摘要： 目前微博已经成为网络舆论传播和挖掘民意的重要平台, 为分析疫情事件对网民情绪的影响, 科学高效地做好防控宣传和舆情引导工作, 为此融合不同的深度学习方法对 2020 年初发生的新冠疫情的微博评论进行情感分析。提出一种基于 RNN(Recursive Neural Network)和 LSTM(Long Short-Term Memory)混合模型并在嵌入层中使用 FastText 词向量表示方法, 以降低词向量中的噪声数据, 从而获得语义丰富且噪声少的高质量词向量, 并与朴素贝叶斯、支持向量机、 RNN、 LSTM 多种情感分析方法进行比较。结果表明, 所提出的情感分析模型正确率达到了 98. 71% , 证明了该模型能有效提升情感分析正确率。

关键词: 情感分析; , 微博语料; , FastText 词向量； , 长短时记忆网络

Abstract: In recent years, microblog has become an important platform for Internet public opinion disseminationand public opinion mining. In order to analyze the impact of epidemic events on Netizens' emotions, we should do a good job in prevention and control publicity and public opinion guidance scientifically and efficiently.Therefore, we integrate different deep learning methods to conduct emotional analysis of microblog comments on the COVID-19 outbreak at the end of 2020. A hybrid model based on RNN(Recursive Neural Network) and LSTM (Long Short-Term Memory) and using the FastText word vector representation in the embedding layer is proposed to reduce the noise data in the word vectors and thus obtain high-quality word vectors with semantically
rich and less noise. Training on Weibo corpora and compared with Bayesian and Support Vector Machine, RNN,LSTM multiple methods, the results show that the accuracy of the emotion analysis model proposed in this paper reaches 98. 71% , which proves that the model can effectively improve the accuracy of emotion analysis.

Key words: emotional analysis; , weibo corpus; , FastText word vector； long and short memory network

中图分类号:

任伟建, 刘圆圆, 计妍, 康朝海. 基于 RNN-LSTM 新冠肺炎疫情下的微博舆情分析[J]. 吉林大学学报(信息科学版), 2022, 40(4): 581-588.

REN Weijian, LIU Yuanyuan, JI Yan, KANG Chaohai. Public Opinion Analysis on Weibo Based on RNN-LSTM in COVID-19[J]. Journal of Jilin University (Information Science Edition), 2022, 40(4): 581-588.