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

Sun

2022

IJERPH

The COVID-19 pandemic caused by SARS-CoV-2 is still raging. Similar to other RNA viruses, SARS-COV-2 is constantly mutating, which leads to the production of many infectious and lethal strains. For instance, the omicron variant detected in November 2021 became the leading strain of infection in many countries around the world and sparked an intense public debate on social media. The aim of this study is to explore the Chinese public’s perception of the omicron variants on social media. A total of 121,632 points of data relating to omicron on Sina Weibo from 0:00 27 November 2021 to 23:59:59 30 March 2022 (Beijing time) were collected and analyzed with LDA-based topic modeling and DLUT-Emotion ontology-based sentiment analysis. The results indicate that (1) the public discussion of omicron is based on five topics, including omicron’s impact on the economy, the omicron infection situation in other countries/regions, the omicron infection situation in China, omicron and vaccines and pandemic prevention and control for omicron. (2) From the 3 sentiment orientations of 121,632 valid Weibo posts, 49,402 posts were judged as positive emotions, accounting for approximately 40.6%; 47,667 were negative emotions, accounting for nearly 39.2%; and 24,563 were neutral emotions, accounting for about 20.2%. (3) The result of the analysis of the temporal trend of the seven categories of emotion attribution showed that fear kept decreasing, whereas good kept increasing. This study provides more insights into public perceptions of and attitudes toward emerging SARS-CoV-2 variants. The results of this study may provide further recommendations for the Chinese government, public health authorities, and the media to promote knowledge about SARS-CoV-2 variant pandemic-resistant messages.

Section: Discussionmentioning

confidence: 99%

Exploring the Chinese Public’s Perception of Omicron Variants on Social Media: LDA-Based Topic Modeling and Sentiment Analysis

Sun

2022

IJERPH

“…Compared to a large number of anti-vaccination discussions on Twitter, similar discourse is rare on Sina Weibo [ 47 ]. Previous studies maintained that pro-vaccine information usually revolves around potential side effects, adverse vaccine reactions, misinformation, and conspiracy theories [ 35 ]. Apart from conspiracy theories, anti-vaccination discussions among the Chinese public showed similar topics.…”

Section: Discussionmentioning

confidence: 99%

“…They found complex emotions in which anger and fear coexisted with trust, solidarity, and hope. Another study comparing American and Chinese posts on Twitter and Sina Weibo revealed differences in public perceptions of COVID-19 among people in different cultures [ 35 ].…”

Section: Introduction and Literature Reviewmentioning

confidence: 99%

Does the COVID-19 Vaccine Still Work That “Most of the Confirmed Cases Had Been Vaccinated”? A Content Analysis of Vaccine Effectiveness Discussion on Sina Weibo during the Outbreak of COVID-19 in Nanjing

Gao

Zhao

Ning

et al. 2021

IJERPH

In July 2021, breakthrough cases were reported in the outbreak of COVID-19 in Nanjing, sparking concern and discussion about the vaccine’s effectiveness and becoming a trending topic on Sina Weibo. In order to explore public attitudes towards the COVID-19 vaccine and their emotional orientations, we collected 1542 posts under the trending topic through data mining. We set up four categories of attitudes towards COVID-19 vaccines, and used a big data analysis tool to code and manually checked the coding results to complete the content analysis. The results showed that 45.14% of the Weibo posts (n = 1542) supported the COVID-19 vaccine, 12.97% were neutral, and 7.26% were doubtful, which indicated that the public did not question the vaccine’s effectiveness due to the breakthrough cases in Nanjing. There were 66.47% posts that reflected significant negative emotions. Among these, 50.44% of posts with negative emotions were directed towards the media, 25.07% towards the posting users, and 11.51% towards the public, which indicated that the negative emotions were not directed towards the COVID-19 vaccine. External sources outside the vaccine might cause vaccine hesitancy. Public opinions expressed in online media reflect the public’s cognition and attitude towards vaccines and their core needs in terms of information. Therefore, online public opinion monitoring could be an essential way to understand the opinions and attitudes towards public health issues.

“…Naïve Bayes model is applied to analyze the collected tweets of the Twitter users to predict their sentiment. Deng et al [11] used data mining approaches and a set of predefined search terms related to COVID-19 to analyze Twitter data. Also, used Latent Dirichlet Allocation (LDA), as topic modeling approach to detect the most popular topics published by the different users to detect and identify the trending topics.…”

Section: Related Workmentioning

confidence: 99%

The Identification of the Top Positive Influential Users of the Social Networks to Help in the Control of Covid-19 Spread

Samir

Gharib²,

Rady³

2022

IJICIS

Covid-19 pandemic is considered the most worldwide problem, and causes horrible crises for all human being. Social networks can play a vital role in the prevention of the spread of the Covid-19 pandemic. The top influential users of social networks like Twitter can have positive or negative effect in the broadcast of useful and same time harmful information about how to deal with the virus, and encourage people to follow up the rules announced by World Health Organization (WHO). So the detection of the top positive and negative influential users can help in the control of the spread of the virus. The proposed approach is based on applying influence maximization solutions to identify the top influential users from Twitter social network graph, and to determine if the influence is positive or not.The proposed approach has four main phases, the first phase is collecting Covid-19 pandemic related tweets dataset and extract the related users and their followers. The second phase is creating a social network graph from the collected dataset. The third phase is using LKG influence maximization approach to identify the most effective users from the social network graph. The last phase is based on using hashtags frequency analysis to be able to identify the type of influence of each top influential user.