Tweet Topics and Sentiments Relating to COVID-19 Vaccination Among Australian Twitter Users: Machine Learning Analysis

Abstract

Background COVID-19 is one of the greatest threats to human beings in terms of health care, economy, and society in recent history. Up to this moment, there have been no signs of remission, and there is no proven effective cure. Vaccination is the primary biomedical preventive measure against the novel coronavirus. However, public bias or sentiments, as reflected on social media, may have a significant impact on the progression toward achieving herd immunity. Objective This study aimed to use machine learning methods to extract topics and sentiments relating to COVID-19 vaccination on Twitter. Methods We collected 31,100 English tweets containing COVID-19 vaccine–related keywords between January and October 2020 from Australian Twitter users. Specifically, we analyzed tweets by visualizing high-frequency word clouds and correlations between word tokens. We built a latent Dirichlet allocation (LDA) topic model to identify commonly discussed topics in a large sample of tweets. We also performed sentiment analysis to understand the overall sentiments and emotions related to COVID-19 vaccination in Australia. Results Our analysis identified 3 LDA topics: (1) attitudes toward COVID-19 and its vaccination, (2) advocating infection control measures against COVID-19, and (3) misconceptions and complaints about COVID-19 control. Nearly two-thirds of the sentiments of all tweets expressed a positive public opinion about the COVID-19 vaccine; around one-third were negative. Among the 8 basic emotions, trust and anticipation were the two prominent positive emotions observed in the tweets, while fear was the top negative emotion. Conclusions Our findings indicate that some Twitter users in Australia supported infection control measures against COVID-19 and refuted misinformation. However, those who underestimated the risks and severity of COVID-19 may have rationalized their position on COVID-19 vaccination with conspiracy theories. We also noticed that the level of positive sentiment among the public may not be sufficient to increase vaccination coverage to a level high enough to achieve vaccination-induced herd immunity. Governments should explore public opinion and sentiments toward COVID-19 and COVID-19 vaccination, and implement an effective vaccination promotion scheme in addition to supporting the development and clinical administration of COVID-19 vaccines.

Revealing Public Opinion Towards COVID-19 Vaccines With Twitter Data in the United States: Spatiotemporal Perspective

“…In general, existing studies have investigated people’s reactions towards COVID-19 vaccines, with a geographical emphasis on the United States [ 14 - 19 ]. Some papers have also studied other countries in the world, including China [ 20 ], South Africa [ 21 ], Australia [ 22 ], the United Kingdom [ 14 , 23 ], Canada [ 24 ], and Africa [ 25 ], and to a global scale [ 26 ]. However, the study period of these works is relatively limited to or predominantly focused on the early stage of the pandemic or up to the end of 2020.…”

What public health campaigns can learn from people’s Twitter reactions on mask-wearing and COVID-19 Vaccines: a topic modeling approach

“…As a major social media platform and a pivotal source for text based public discourse, Twitter has been studied to understand public reactions during various public health crises, including the Covid-19 pandemic (e.g. Abd-Alrazaq et al, 2020;Doogan et al, 2020;Kwok et al, 2021;Liu et al, 2020). Research on the role of Twitter in face of public health crises has focused on two directions: (a) Twitter as an information source for emergency responses management and (b) Twitter as the collective outcome for public perceptions and attitudes about health and risk issues.…”

“…While most research identified general topics related to the COVID-19 outbreak such as origin, prevention, and impact (e.g. Abd-Alrazaq et al, 2020;Liu et al, 2020), only a few focused on non-pharmaceutical interventions (NPIs) (Doogan et al, 2020) or vaccination (Kwok et al, 2021). Therefore, we intended to study Twitter discourse on two preventive measures: mask-wearing and vaccination, with a particular focus on the United States, where the highest number of confirmed cases and deaths were confirmed (John Hopkins Coronavirus Resource Center, n.d.), and unsatisfactory compliance rate for mask-wearing (Igielnik, 2020, June 23, June 23) and moderate hesitancy level for vaccination were revealed in earlier surveys (O'Keefe, 2020, Aug. 7, August 7).…”

“…To date, limited is known about the overall valence of Twitter discourse about specific NPI measures such as mask wearing. Kwok et al's (Kwok et al, 2021) sentiment analysis of Australia-based tweets revealed that two-thirds of the tweets about COVID-19 vaccination were positive and the remaining one-third were negative. However, there is a paucity of knowledge about how such difference in valence can be attributed to the difference in their underlying topics or how it evolved over time.…”

Revealing public opinion towards COVID-19 vaccines with Twitter Data in the United States: a spatiotemporal perspective

“…Additionally, user locational information enables researchers to investigate the spatiotemporal patterns of the public’s opinions and attitudes. In general, existing studies have investigated people’s reactions towards COVID-19 vaccines, with a heavy focus on the US [10-15] and also extends to other countries in the world, including China [16], South Africa [17], Australia [18], United Kingdom [19-20], Canada [21, 11], Africa [22] and to a global scale [23]. However, the study period of these works is relatively limited to or predominantly focused on the early stage of the pandemic or up to the end of 2020, without covering early 2021, the period of mass systemic vaccine implementation in many countries.…”