Analysis of The Multilayer Perceptron Algorithm on Twitter User’s Sentiment Towards The COVID-19 Vaccine

Abstract

The World Health Organization (WHO) declared COVID-19 a global pandemic due to its rapid spread and infection of people worldwide. The emergence of COVID-19 vaccines has garnered both support and rejection from the public. Some people support the vaccines, while others remain cautious, even though the government provides them for free. The procurement of coronavirus vaccines has generated diverse opinions in society. COVID-19 vaccines have become a trending topic on social media, particularly on Twitter. This research aims to explore public opinions on the COVID-19 vaccine. The methods used in this study include data collection, text preprocessing, TF-IDF, multilayer perceptron algorithm, and testing with confusion matrices. Out of a total of 228,208 positive, negative, and neutral opinions from Twitter users about the COVID-19 vaccine, with a training-to-testing ratio of 90% to 100%, the model will learn more by using a large amount of training data. The performance results of this research obtained the highest accuracy of 81.2%, precision of 83.8%, and recall of 71.2%. The results of sentiment analysis can be seen in the public opinions on the COVID-19 vaccine, which are divided into three categories: 35% positive opinions, 16.3% negative opinions, and 48.7% neutral opinions. The word cloud results show that positive opinions revolve around three topics: availability, cost, and dosage. Negative opinions from Twitter users about the COVID-19 vaccine focus on two main issues: vaccine side effects and deaths. Neutral opinions cover three topics, including dosage, availability, age, and expiration date