To Vaccinate or not to Vaccinate? Analyzing $\mathbb{X}$ Power over the Pandemic

TL;DR

The paper addresses how public sentiment toward COVID-19 vaccines manifests on $\mathbb{X}$ by assembling a large tweet corpus (approximately $0.4$ million) and applying NLP sentiment analysis (VADER, TextBlob), complemented by a manually labeled set of $200$ tweets used to train and compare multiple one-class classifiers (OC-SVM, SVDD, ESVDD, S-SVDD variants) including NS-SVDD with Newton optimization. It introduces the S-SVDD framework with a boundary described by $R$, $\mathbf{a}$, and $\mathbf{Q}$, optimized via an augmented Lagrangian that includes a class-variance regularization term $\psi$ and variants $\psi_1$–$\psi_4$, and uses hyperparameter search guided by $GM=\sqrt{tpr\times tnr}$. The study finds that globally, vaccine sentiment is predominantly positive, while country-level analyses reveal substantial regional differences, with NS-SVDD variants often delivering the best geometric-mean performance across positive and negative classes. Overall, the work offers a scalable, interpretable analytics pipeline for monitoring vaccine hesitancy and informing public-health messaging and rollout strategies, leveraging both textual analytics and targeted one-class classification models.

Abstract

The COVID-19 pandemic has profoundly affected the normal course of life -- from lock-downs and virtual meetings to the unprecedentedly swift creation of vaccines. To halt the COVID-19 pandemic, the world has started preparing for the global vaccine roll-out. In an effort to navigate the immense volume of information about COVID-19, the public has turned to social networks. Among them, $\mathbb{X}$ (formerly Twitter) has played a key role in distributing related information. Most people are not trained to interpret medical research and remain skeptical about the efficacy of new vaccines. Measuring their reactions and perceptions is gaining significance in the fight against COVID-19. To assess the public perception regarding the COVID-19 vaccine, our work applies a sentiment analysis approach, using natural language processing of $\mathbb{X}$ data. We show how to use textual analytics and textual data visualization to discover early insights (for example, by analyzing the most frequently used keywords and hashtags). Furthermore, we look at how people's sentiments vary across the countries. Our results indicate that although the overall reaction to the vaccine is positive, there are also negative sentiments associated with the tweets, especially when examined at the country level. Additionally, from the extracted tweets, we manually labeled 100 tweets as positive and 100 tweets as negative and trained various One-Class Classifiers (OCCs). The experimental results indicate that the S-SVDD classifiers outperform other OCCs.

Figures (2)

• Figure 1: Tweets' sentiment analysis flow
• Figure 2: Sentiment analysis of tweets