Characterizing Twitter Discussions About Coronavirus Vaccines in the United States: A Topic Modelling Analysis (Preprint)
BACKGROUND A coronavirus vaccine that works is considered a game-changer in the battle against the unprecedented pandemic. News and social media discussions have been extensively covered the issue of coronavirus vaccines, with a mixture of advocacies, concerns, rumors and conspiracy theories. OBJECTIVE This study aims to uncover the emerging themes in social media discussions regarding the potential coronavirus vaccines. METHODS This study employ topic modelling to analyze Tweets related to coronavirus vaccines at the start of the COVID-19 in the United States (February 21 to March 20, 2020). We created a predefined query (e.g., "COVID" AND "vaccine") to extract the tweet text and metadata (number of followers of the Twitter account and engagement metrics based on likes, comments and retweeting) from the Meltwater database. After pre-processing the data, we tested Latent Dirichlet Allocation models with different solutions for identifying topics associated with tweets. The topic model with 20 topics provided the best topic coherence, and each topic was interpreted based on its top associated terms. RESULTS In total, we analyzed 100,209 tweets related to coronavirus vaccines. The 20 topics were further collapsed based on their similarities, resulting in seven big themes. Our analysis characterized 26.3% of the tweets as News Related to Coronavirus and Vaccine Development, 25.4% as General Discussion and Information Seeking of Coronavirus, 12.9% as Financial Concerns, 12.7% as Venting Negative Emotions, 9.9% as Prayers and Call for Positivity, 8.1 as Efficacy of Vaccine and Treatment and 4.9% as Conspiracies. Different themes demonstrated some changes over time, mostly in a close association with news or events related to the progress of vaccine developments. Users with a large number of followers (also known as key opinion leaders) preferred to discuss the themes of conspiracy theories, efficacy of vaccines and treatments, and financial concerns over other themes. The engagement levels of different themes were similar except for venting negative emotions. CONCLUSIONS This study concluded that financial concerns emerged as one important concern among the public regarding the potential coronavirus vaccines. The discussions of vaccines considerably mixed with political discussions, which suggests that the issue of coronavirus vaccines is politicized in the US. Only a small proportion of tweets were concerned about conspiracy theories, but their impact can be amplified by key opinion leaders and its relatively higher engagement level with the audiences. CLINICALTRIAL N.A.