Using data mining technology to analyse the spatiotemporal public opinion of COVID-19 vaccine on social media

Abstract

Purpose The deployment of vaccines is the primary task in curbing the COVID-19 pandemic. The purpose of this paper is to understand the public’s opinions on vaccines and then design effective interventions to promote vaccination coverage. Design/methodology/approach This paper proposes a research framework based on the spatiotemporal perspective to analyse the public opinion evolution towards COVID-19 vaccine in China. The framework first obtains data through crawler tools. Then, with the help of data mining technologies, such as emotion computing and topic extraction, the evolution characteristics of discussion volume, emotions and topics are explored from spatiotemporal perspectives. Findings In the temporal perspective, the public emotion declines in the later stage, but overall emotion performance is positive and stabilizing. This decline in emotion is mainly associated with ambiguous information about the COVID-19 vaccine. The research progress of vaccines and the schedule of vaccination have driven the evolution of public discussion topics. In the spatial perspective, the public emotion tends to be positive in 31 regions, whereas local emotion increases and decreases in different stages. The dissemination of distinctive information and the local epidemic prevention and control status may be potential drivers of topic evolution in local regions. Originality/value The analysis results of media information can assist decision-makers to accurately grasp the subjective thoughts and emotional expressions of the public in terms of spatiotemporal perspective and provide decision support for macro-control response strategies and risk communication.

Applications of Social Media and Digital Technologies in COVID-19 Vaccination: Scoping Review

“…Fifty-three studies applied social media for topic analysis on COVID-19 vaccination. Topic analysis methods included latent Dirichlet allocation (LDA) topic modeling (n=24) [ 20 , 23 , 25 , 31 , 34 , 35 , 40 , 47 , 50 , 51 , 54 - 56 , 58 , 60 , 61 , 64 , 87 - 93 ], manual coding (n=17) [ 57 , 80 , 94 - 108 ], and other algorithms (n=12) [ 26 , 43 , 62 , 109 - 117 ]. Table 2 summarizes the provaccine and antivaccine topics on COVID-19 vaccines present on social media.…”

“…Additionally, public discussions were mainly driven by COVID-19 vaccine–related news, major social events, pandemic severity, and statements issued by authorities [ 23 , 26 , 34 , 51 , 58 , 87 , 89 ]. Regarding information sources, authoritative and reliable information disseminators, such as government agencies, major media outlets, and key opinion leaders, played massively influential roles in polarizing opinions, which can amplify or contain the spread of misinformation among target audiences.…”

“…Fifty-three studies applied social media for topic analysis on COVID-19 vaccination. Topic analysis methods included latent Dirichlet allocation (LDA) topic modeling (n=24) [20,23,25,31,34,35,40,47,50,51,[54][55][56]58,60,61,64,[87][88][89][90][91][92][93], manual coding (n=17) [57,80,[94][95][96][97][98][99][100][101][102][103][104][105][106][107][108], and other algorithms (n=12) [26,43,62,[109][110][111][112][113][114]…”

Data mining analytics investigate WeChat users’ behaviours: online social media and social commerce development

“…Therefore, making good use of social media can promote knowledge sharing and collaboration within organizations (Iandoli et al , 2021). For marketing researchers, the influence of companies or individuals on consumers through online social media has been explored, including the social influence of virtual communities or the influence of online critics (social influencers), word-of-mouth (WOM) marketing and user-generated content and comments (UGC), as well as causes and processes of information diffusion via the internet (Li et al , 2022). With the rapid development and application of information technology, online social media have gradually become an important channel for people to transmit information and change business operation modes, especially during the COVID-19 epidemic (Lee et al , 2021).…”

A study on the influence of online reviews of new products on consumers’ purchase decisions: An empirical study on JD.com

“…Blei et al (2003) proposed the using of Perplexity as a criterion for determining the number of topics, but it tends to lead to too much similarity between topics. Considering the generalization ability of the model and the effect of topic extraction, this paper uses the Perplexity − Var method (Welch, 2003;Li T. et al, 2022), which takes into account the perplexity and intertopic similarity, to calculate the optimal number of topics. The method measures the structural stability of topics by their scatter and penalizes excessive overload of topics, minimizing the number of topics while ensuring maximum distinction between topics.…”