COVID-19 Vaccines Related User’s Response Categorization Using Machine Learning Techniques

• DOI: 10.3390/computation10080141
• Publication Date: 2022-08-19T01:39:21Z
• Authors: Ahmed Shahzad; Bushra Zafar; Nouman Ali; Uzma Jamil; Abdulaziz Jaralla...; Muhammad Assam; Nivin A. Ghamry; Elsayed Tag Eldin
• Keywords: Sentiment Analysis

Respiratory viruses known as coronaviruses infect people and cause death. The multiple crown-like spikes on the virus’s surface give them name “corona”. pandemic has resulted in a global health crisis it is expected that every year we will have to fight against different COVID-19 variants. In this critical situation, existence of vaccinations provides hope for mankind. Despite severe vaccination campaigns recommendations from experts government, perceptions regarding risks share their views experiences social media platforms. Social attitudes these types are influenced by positive negative effects. analysis such opinions can help determine trends formulate policies increase acceptance. This study presents methodology sentiment perspectives related vaccinations. research performed five include Sinopharm, Pfizer, Moderna, AstraZeneca, Sinovac Twitter platform extracted using crawling. To effectively perform research, tweets datasets categorized into three groups, i.e., positive, natural. For classification, machine learning classifiers used Random Forest (RF), Naive Bayes (NB), Decision Tree (DT), Logistic Regression (LR), Support Vector Machine (SVM). It should be noted tree classifier achieves highest classification performance all compared other algorithms. Vaccine Tweets with Sentiment Annotation (CVSA), accuracy obtained 93.0%, AstraZeneca vaccine dataset 90.94%, Pfizer 91.07%, 88.01% Moderna dataset, 92.8% accuracy, 93.87% Sinopharm respectively. quantitative comparisons demonstrate proposed better state-of-the-art research.