Analisis Sentimen Vaksinasi Booster Berdasarkan Twitter Menggunakan Algoritma Naïve Bayes dan K-NN

Abstract

Covid-19 or the corona virus has spread throughout the world, one of which is Indonesia. There have been many problems due to this virus for 2 years in Indonesia, and various efforts and policies have been made by the government to control the impact that does not become worse by this corona virus, these efforts are vaccination actions against the Indonesian people, and in early 2022 the government started a new program, namely booster vaccination. Many people are pro and contra to the program on social media Twitter. This study was conducted with the aim of knowing the sentiment of Indonesians towards booster vaccination in Indonesia.The data obtained as many as 2000 tweets obtained from the keyword "booster vaccine" on Twitter. Then the data is divided into training data and test data (training) then made into three different portions, namely 60/40, 70/30, and 80/20. The test results are that the best performance is found in testing a portion of 80% of the training data 20% of the test data using the K-NN algorithm, the test produced the highest value results, namely 78.62% accuracy and AUC 0.845 and categorized as good classification. The results show that the K-NN algorithm model with an 80% portion of training data is the best in the classification of booster vaccination sentiment analysis. The sentiment results in the test data were positive with 303 tweet data and negative sentiment totaled 93 tweet data. The results of more positive sentiments show that booster vaccinations in Indonesia are acceptable and get a lot of support from the Indonesian people on social media Twitter.

Klasifikasi Sentimen Masyarakat di Twitter terhadap Ganjar Pranowo dengan Metode K-Nearest Neighbor

“…Feature Selection adalah tahapan yang berfungsi untuk mengurangi jumlah fitur yang kurang relevan dalam menentukan nilai kelas target dengan menggunakan nilai batas ambang [24]. Fitur yang kurang relevan akan diabaikan dalam penentuan kelas target.…”