Text Mining Approaches to Analyze Public Sentiment Changes Regarding COVID-19 Vaccines on Social Media in Korea

Abstract

The COVID-19 pandemic has affected the entire world, resulting in a tremendous change to people’s lifestyles. We investigated the Korean public response to COVID-19 vaccines on social media from 23 February 2021 to 22 March 2021. We collected tweets related to COVID-19 vaccines using the Korean words for “coronavirus” and “vaccines” as keywords. A topic analysis was performed to interpret and classify the tweets, and a sentiment analysis was conducted to analyze public emotions displayed within the retrieved tweets. Out of a total of 13,414 tweets, 3509 were analyzed after preprocessing. Eight topics were extracted using the Latent Dirichlet Allocation model, and the most frequently tweeted topic was vaccine hesitation, consisting of fear, flu, safety of vaccination, time course, and degree of symptoms. The sentiment analysis revealed a similar ratio of positive and negative tweets immediately before and after the commencement of vaccinations, but negative tweets were prominent after the increase in the number of confirmed COVID-19 cases. The public’s anticipation, disappointment, and fear regarding vaccinations are considered to be reflected in the tweets. However, long-term trend analysis will be needed in the future.

Social media and attitudes towards a COVID-19 vaccination: A systematic review of the literature

“…Events that were identified as those that triggered an increase in the positive emotions towards vaccination were: the announcement about the vaccines' effectiveness, 99−102 the arrival of the vaccines in UK hospitals, 99 the announcement of the first human vaccine trial (UK Twitter and Facebook users) and Donald Trump's announcement regarding a vaccine being ready in a few weeks (US Twitter and Facebook users), 100 as well as the decrease in number of positive COVID-19 cases in Korea. 50 Some of the events that were classified as stimulating negative discussions surrounding COVID-19 vaccines were: popularity of conspiracy theories (related to Bill Gates and microchips), 103 the authorization in the UK of the Pfizer BioNTech COVID19 vaccine, 99 the UK opting out of the European Union vaccination scheme and halting of the phase III vaccine trials at the University of Oxford owing to safety concerns (documented among the UK and USA users), 100 the growth in the occurrence of "fake news" and "misinformation" on social media, 100 the increase in the number of COVID-19 infected cases in Korea (as observed among Korean Twitter users). 50 Finally, Table 5 presents a synthetic summary the main findings of each category of studies included in showed that trust was the most predominant emotion, followed by anticipation, fear, sadness, etc.…”

Perceptions and attitudes towards Covid-19 vaccines: narratives from members of the UK public

“…Studies have consistently shown that social media were among the top sources of information regarding Covid-19 vaccines (Chaudhary et al 2021 ; Al-Mulla et al 2021 ; Belsti et al 2021 ). Various Twitter analysis studies were conducted in different countries around the globe (Chen et al 2021 ; Shim et al 2021 ; Guntuku et al 2021 ) showing high levels of engagement of social media platforms in Covid-19 related topics, including the vaccine. In our study, the majority of participants felt that social media had influenced others’ perceptions of Covid-19 vaccines but not theirs.…”

Fear of Infection and Sufficient Vaccine Reservation Information Might Drive Rapid Coronavirus Disease 2019 Vaccination in Japan: Evidence from Twitter Analysis

“…In previous works of large-scale Twitter analyses, after preprocessing, there are mainly four types of NLP methods: n-gram token analysis [12,15,20,21], sentiment analysis [12,14,15,[20][21][22][23][24][25], topic modelling [12,14,15,20,[22][23][24][25], and geographical analysis [22,24]. The geographical analysis is less important in our work because the range of our research is a whole country instead of subareas.…”

“…In Google Trends analysis, correlations were calculated between reported cases of infectious disease and the trends of search for relevant keywords. In Twitter analyses, correlations between the daily infectious or death cases, and the number of related tweets or sentiment scores, were also investigated [24,25]. In this work, correlation analyses were adopted to find out the factors from the top unigrams that are most related to COVID-19 vaccination campaign.…”