ABSTRACT
Objective: This study aimed to categorize and analyze the public response toward third/booster shots of COVID-19 on Twitter. Methods: We downloaded the COVID-19 vaccine booster shots related Tweets using the Twitter API. The collected Tweets were pre-processed to prepare them for analysis by (1) removing non-English language tweets, retweets, emojis, emoticons, non-printable characters, the punctuation marks, and the prepositions, (2) anonymizing the identity of the users, and (3) normalizing various forms of the same words. We used the state-of-the-art BertTopic modeling library to identify the most popular topics. Results: Of 165,048 Tweets collected, 36,908 Tweets were analyzed in this study. From these tweets, we identified 9 topics, which were about Biden administration, Pfizer & BioNTech, Moderna, Johnson & Johnson, eligibility for booster shots, side effects, Donald Trump, variants of the Novel Coronavirus, and conspiracy theory & propaganda. The mean of sentiment was positive in all topics. The lowest and highest mean of sentiments were for the Donald Trump topic (0.0097) and the Johnson & Johnson topic (0.1294), respectively. Conclusions: The topics identified in this study not only accurately reflect the contemporary COVID-19 discussion, but also the high degree of politicization in the USA. While the latter might be a result of our rejection of non-English tweets, it is reassuring to see our fully automated, unsupervised pipeline reliably extract such global features in the data at scale. We, therefore, believe that the methodology presented in this study is mature and useful for other infoveillance studies on a wide variety of topics. © 2022 The Author(s). Published with license by Taylor & Francis Group, LLC.
ABSTRACT
The world is witnessing unprecedented times as the novel Coronavirus disease (COVID-19) has already conquered and locked down most of the globe. While some indications suggest that the COVID-19 curve is starting to flatten, as of May 2020, we still see constant linear growth in cases and fatalities. Even worse, it is speculated that the situation may further deteriorate with a possible second wave. As governments around the world continue to impose increasingly stringent measures to fight and limit the spread of the pandemic, Artificial Intelligence (AI) tools can play a significant role in the public health surveillance and diagnostics relating to COVID-19. AI is being heavily leveraged in the diagnosis of COVID-19, prediction of its severity for infection, and the discovery of related drugs and vaccines. However, several challenges can impede the exploitation of AI amid the COVID-19 pandemic such as lack of data, privacy, and maturity of AI applications. This chapter discusses the main AI opportunities and challenges in the fight against the COVID-19 pandemic. © 2021, Springer Nature Switzerland AG.