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

2025-03-04

AI Summary

This study addresses the critical problem of public sentiment assessment toward COVID-19 vaccines, leveraging multilingual textual data from X (formerly Twitter) across multiple countries to analyze sentiment polarity and its spatiotemporal evolution and geographic heterogeneity. Methodologically, it pioneers the application of One-Class Classifiers—particularly the Support Vector Data Description (S-SVDD)—to vaccine sentiment modeling under small-sample, weakly-supervised conditions, thereby mitigating severe annotation scarcity. The approach integrates cross-national fine-grained sentiment visualization with keyword and hashtag statistical analysis to uncover cognitive heterogeneity. Experimental results show that global sentiment is predominantly positive, yet exhibits marked country-level divergence. S-SVDD achieves superior accuracy over state-of-the-art one-class classifiers using only 100 positive or negative samples per class, demonstrating its efficacy and robustness in low-resource舆情 analysis. This work provides a scalable methodological framework and empirically grounded insights for public health sentiment monitoring.

Technology Category

• Natural Language Processing: Text Classification & Sentiment Analysis
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Social Networks and Social Media: Fairness and bias in social network and social media analysis

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.

Problem

• Analyzing public sentiment on COVID-19 vaccines using Twitter data.
• Exploring global variations in vaccine perception through sentiment analysis.
• Evaluating One-Class Classifiers for vaccine-related tweet classification.

Innovation

• Sentiment analysis using natural language processing
• Textual analytics and data visualization techniques
• One-Class Classifiers for tweet sentiment classification