Classification of Booster Vaccination Symptoms Using Naive Bayes Algorithm and C4.5

Abstract

Covid-19 is a respiratory infection that is transmitted through the air. The first case was reported on March 2, 2020, to be precise in Depok, West Java, Indonesia. To reduce the number of corona virus sufferers, the government has made various efforts including policies to limit activities outside the home, online learning, work from home, and even worship activities. To reduce the number of people infected with the Covid-19 virus, efforts are being made, one of which is the provision of vaccines. In this study, the types of booster vaccines are Pfizer and AstraZeneca. Due to the symptoms caused by the condition of the patient after vaccination, the researchers used the Naive Bayes Algorithm and C4.5 methods with attributes including gender, age, comorbidities (comorbidities), temperature, blood pressure, Covid 19 survivors > 1 month, pregnant condition, type of vaccine. primer and booster vaccine types which aim to get the highest accuracy value between the two algorithm methods which are tested using cross validation on the RapidMiner Studio tool. And obtained the Naive Bayes algorithm method with the highest accuracy value of 78.82%. Keywords: Covid 19, booster, AEFI, Naive Bayes, C4.5, Rapid Miner

Keywords

• Covid 19
• Booster
• Naive Bayes
• C4.5
• Rapid Miner