Scholarlink

This study explores the vast realm of Twitter, leveraging its real-time data on public opinions and sentiments about COVID-19 vaccinations, where diverse voices converge in succinct tweets. By applying sentiment analysis and natural language processing (NLP) techniques, we unveil public perceptions of COVID-19 vaccinations, analysing a dataset of over ten thousand tweets from January to April 2021. Our approach identifies prevailing themes within these tweets, translating them into digestible narratives, providing healthcare experts with unique insights into public reactions to health interventions as they unfold. The analytical pipeline begins with accessing Twitter’s API and authentication tokens, followed by NLP techniques to process raw tweets. Sentiment analysis then categorizes tweets as positive, negative, or neutral, allowing us to gauge the collective emotional pulse. From these categorized tweets, key themes are extracted, giving a high-level view of the main conversations, like crafting a masterpiece where each algorithmic step unveils insights from vast data. Ultimately, this study offers a deep dive into the world of tweets, transforming them into actionable insights and providing a real-time radar for the health community to navigate the evolving landscape of public opinion.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Vaccine Sentiment Analysis: A Twitter Study Using NLP and ML Approach

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Subash Chandra Bose Jaganathan,
  • M. V. Sreeram,
  • Badrikanath Praharaj,
  • R. Sanjay,
  • Soumik Roy,
  • Yashraj Jyoti Sanjay Kastode,
  • A. Priyadharshini

摘要

This study explores the vast realm of Twitter, leveraging its real-time data on public opinions and sentiments about COVID-19 vaccinations, where diverse voices converge in succinct tweets. By applying sentiment analysis and natural language processing (NLP) techniques, we unveil public perceptions of COVID-19 vaccinations, analysing a dataset of over ten thousand tweets from January to April 2021. Our approach identifies prevailing themes within these tweets, translating them into digestible narratives, providing healthcare experts with unique insights into public reactions to health interventions as they unfold. The analytical pipeline begins with accessing Twitter’s API and authentication tokens, followed by NLP techniques to process raw tweets. Sentiment analysis then categorizes tweets as positive, negative, or neutral, allowing us to gauge the collective emotional pulse. From these categorized tweets, key themes are extracted, giving a high-level view of the main conversations, like crafting a masterpiece where each algorithmic step unveils insights from vast data. Ultimately, this study offers a deep dive into the world of tweets, transforming them into actionable insights and providing a real-time radar for the health community to navigate the evolving landscape of public opinion.