COVID-19 Vaccination Opinions in Education-Related Tweets

ABSTRACT

The coronavirus pandemic has forced authorities to take unprecedented measures, including the temporary closure of business and the instauration of national and regional lockdowns. The educational system, one of the key components of the society, has also been disrupted, as many schools and universities have moved their courses online for prolonged periods. With the introduction of the first vaccine on December 8, 2020, social media users have reacted by posting messages supporting or rejecting the vaccination process. In this context, the present paper aims to analyze the opinions regarding COVID-19 vaccination in education-related tweets. A dataset containing 102,805 English tweets published in the month following the beginning of the vaccination process has been collected. Several classical machine learning and deep learning algorithms have been compared and the best-performing classifier, RoBERTa, has been selected and applied for determining the stance of the collected tweets, as in favor, against or neutral. The evolution of the opinions has been put in correspondence with the main events that have occurred during the analyzed period, while the main discussion topics have been outlined using the Latent Dirichlet Allocation and n-gram analysis. The obtained results can be useful for authorities looking to better understand the opinions of the parents, students, teachers, and general public. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.