Mining the vaccination willingness of China using social media data. (February 2023)

• Record Type: Journal Article
• Authors: Ding, Jiaming; Wang, Anning; Zhang, Qiang
• Is Part Of: International journal of medical informatics. Volume 170(2023)
• Publication Date: 2023-02
• Subjects: Vaccination willingness -- Social media -- COVID-19 -- Sentiment analysis -- Information dissemination effect; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2022.104941
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: Propose a new methodological tool for mining the public vaccination willingness. Employ a new fusion sentiment analysis model to analyze the blog sentiments. Utilize an information dissemination effect index to calculate the blog dissemination effect. Fuse innovatively the sentiment distribution and dissemination effect for quantifying the vaccination willingness. Abstract: Objective : Vaccination is one of the most powerful and effective protective measures against Coronavirus disease 2019 (COVID-19). Currently, several blogs hold content on vaccination attitudes expressed on social media platforms, especially Sina Weibo, which is one of the largest social media platforms in China. Therefore, Weibo is a good data source for investigating public opinions about vaccination attitudes. In this paper, we aimed to effectively mine blogs to quantify the willingness of the public to get the COVID-19 vaccine. Materials and Methods : First, data including 144, 379 Chinese blogs from Weibo, were collected between March 24 and April 28, 2021. The data were cleaned and preprocessed to ensure the quality of the experimental data, thereby reducing it to an experimental dataset of 72, 496 blogs. Second, we employed a new fusion sentiment analysis model to analyze the sentiments of each blog. Third, the public's willingness to get the COVID-19 vaccine was quantified using the organic fusion of sentiment distribution and information dissemination effect. Results : (1) The intensity of bloggers' sentiment toward COVID-19 vaccines changed over time. (2) The extremum of positive and negative sentiment intensities occurred when hot topics related to vaccines appeared. (3) The study revealed that the public's willingness to get the COVID-19 vaccine and the actual vaccination doses shares a linear relationship. Conclusion : We proposed a method for quantifying the public's vaccination willingness from social media data. The effectiveness of the method was demonstrated by a significant consistency between the estimates of public vaccination willingness and actual COVID-19 vaccination doses.