Enhancing Sentiment Analysis of User Response for COVID-19 Vaccinations Tweets Using SentiWordNet-Adjusted VADER Sentiment Analysis (SAVSA): A Hybrid Approach

In the contemporary digital era, social media platforms have emerged as invaluable sources of information and trends, providing essential insights into public sentiment. The extraction of meaningful insights from the vast sea of unstructured social media data poses a considerable challenge. This study is motivated by the imperative to enhance sentiment classification accuracy within the realm of social media mining, with a specific focus on Twitter data, particularly related to COVID-19 vaccination. Text mining assumes a pivotal role in deciphering user-generated content within the dynamic landscape of social media. The innovative approach revolves around refining sentiment classification through a dual-phase process involving SentiWordNet-based scoring and VADER sentiment analysis. By synergizing these methodologies, this research work’s goal is to elevate the precision of sentiment representation in tweets pertaining to COVID-19 vaccination. Through comprehensive evaluation, including the assessment of the Performance of the SentiWordNet-Adjusted VADER Sentiment Analysis (SAVSA) Model using classification algorithm, the effectiveness of the proposed approach becomes evident. This research advances sentiment analysis in the context of social media mining, tailored to the intricacies of Twitter's dynamic environment and focusing on responses to COVID-19 vaccination. By embracing crucial steps such as data scraping, meticulous pre-processing, strategic vectorization, hybrid sentiment polarity assignment, classification tactics, and rigorous evaluation, this study presents a comprehensive framework. In essence, this comprehensive approach holds the potential to shape the trajectory of sentiment analysis within the dynamic landscape of digital communication, specifically within the context of COVID-19 vaccination related Twitter data.