The Evolution of Public Opinion and Its Emotion Analysis in Public Health Emergency Based on Weibo Data

Jiazheng Sun (), Xiaodong Zhang () and Shaojuan Lei ()
Additional contact information
Jiazheng Sun: University of Science and Technology Beijing
Xiaodong Zhang: University of Science and Technology Beijing
Shaojuan Lei: University of Science and Technology Beijing

A chapter in LISS 2022, 2023, pp 415-434 from Springer

Abstract: Abstract Since the occurrence of the Corona Virus Disease 2019, relevant online public opinion has spread rapidly, which has had an important impact on social order. How to identify, prevent and control public opinion crisis of public health emergencies has become a practical problem that urgently needs to be studied. First data source comes from Weibo comments, comparing with the three models of Naive Bayesian Model, Support Vector Machine and Logistic Regression, Long Short Term Memory (LSTM) model based on word to vector (Word2vec) model is selected for emotion classification. Secondly, the evolution of public opinion is divided into three stages base to the Baidu search index, use visualization methods to study emotional tendencies at various stages and analyze the temporal and spatial laws of public opinion. At last, according to the evolution law and characteristics of public opinion in each stage, relevant optimization strategies are proposed. Research shows, the Word2Vec-LSTM model can effectively predict the emotional state of netizens; analyzes the law of public opinion evolution of public health emergencies, provide a basis for optimizing the network environment and preventing public opinion crisis.

Keywords: Corona virus disease 2019; Emotion analysis; Word2Vec-LSTM model; Public opinion evolution (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-99-2625-1_33

Ordering information: This item can be ordered from
http://www.springer.com/9789819926251

DOI: 10.1007/978-981-99-2625-1_33

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().