Cross-Platform Comparative Study of Public Concern on Social Media during the COVID-19 Pandemic: An Empirical Study Based on Twitter and Weibo.

Yi Yang,Wen Deng

doi:10.3390/ijerph18126487

Abstract

The COVID-19 pandemic has created a global health crisis that has affected economies and societies worldwide. During these times of uncertainty and crisis, people have turned to social media platforms as communication tools and primary information sources. Online discourse is conducted under the influence of many different factors, such as background, culture, politics, etc. However, parallel comparative research studies conducted in different countries to identify similarities and differences in online discourse are still scarce. In this study, we combine the crisis lifecycle and opinion leader concepts and use data mining and a set of predefined search terms (coronavirus and COVID-19) to investigate discourse on Twitter (101,271 tweets) and Sina Weibo (92,037 posts). Then, we use a topic modeling technique, Latent Dirichlet Allocation (LDA), to identify the most common issues posted by users and temporal analysis to research the issue’s trend. Social Network Analysis (SNA) allows us to discover the opinion leader on the two different platforms. Finally, we find that online discourse reflects the crisis lifecycle according to the stage of COVID-19 in China and the US. Regarding the status of the COVID-19 pandemic, users of Twitter tend to pay more attention to the economic situation while users of Weibo pay more attention to public health. The issues focused on in online discourse have a strong relationship with the development of the crisis in different countries. Additionally, on the Twitter platform many political actors act as opinion leaders, while on the Weibo platform official media and government accounts control the release of information.

Highlights

Social media platforms such as Twitter and Weibo are regarded as interactive communication tools for public debate and discourse [1] that reduce the cost of communication between users [2,3]; individuals can express their own opinions on public issues and interact with likeminded people spontaneously [4]
We compared the topics discussed on Twitter and Weibo in the context of the COVID-19 pandemic during the same period
Through Latent Dirichlet Allocation (LDA) analysis, we found that, in the predominantly US social networks, represented by Twitter, participants were more concerned about the impact of COVID-19 on the economy and science and technology issues

Summary

Introduction

Social media platforms such as Twitter and Weibo are regarded as interactive communication tools for public debate and discourse [1] that reduce the cost of communication between users [2,3]; individuals can express their own opinions on public issues and interact with likeminded people spontaneously [4]. The huge volume of data available on social media can help us understand the feelings of users about a certain issue or event, as these platforms store individual discourse. It is noteworthy that the Chinese state separates its citizens from the rest of the world through its firewall; this information control method may influence the expression of online discourse [6]. Due to this reason, Chinese social media users occupy an important position in the global Internet, they have received relatively less attention [7]. Few issues generate worldwide interest, so the opportunities to perform comparative study in different countries are limited

Objectives

Methods

Results

Conclusion