COVID-19 World Vaccine Adverse Reactions Based on Machine Learning Clustering Algorithm

Abstract

In December 2019, a novel coronavirus, now named SARS-CoV-2, caused a series of acute atypical respiratory diseases in Wuhan, Hubei province, China. It triggered several acute atypical respiratory diseases. COVID-19 was the name given to the virus's disease. The infection is human-to-human transmissible, and it has triggered a global pandemic. Vaccines against COVID-19 are an essential global intervention to control the current pandemic situation and in a fairly short time, several vaccines have been developed to try to control the situation but have also led to consequences in the form of adverse reactions. Clustering algorithms have been used in computational intelligence and digital analysis, which is one of the areas that has taken this into account. Clustering can be described as a method of grouping similar data into one population or cluster and separating unrelated data into another. For clustering COVID-19 vaccine adverse reactions datasets, a variety of clustering algorithms are used. The objective of this paper is to use the clustering algorithms used in the case of COVID-19 Vaccine Adverse Reactions datasets, demonstrating how these algorithms help to provide accuracy for clustering the COVID-19 Vaccine Adverse Reactions. This study compared four clustering algorithms using the WEKA tool. Furthermore, it details the datasets in terms of different variables of precision, cluster case, number of iterations, time, and present the findings of these papers, and which clustering algorithms used and the accuracy of these algorithms. It is found that the clustering algorithm k-means is used widely in different types of the COVID-19 vaccine adverse reactions datasets with high accuracy.