Perbandingan Metode KNN, Decision Tree, dan Naïve Bayes Terhadap Analisis Sentimen Pengguna Layanan BPJS

BPJS is really helpful because one of its goal is to provide good service for the member in terms of healthiness. But, when there’s many people using the service, then it will cause more pros and contras. Therefore, researcher will be doing sentiment analysis in the field of data mining towards bpjs users on social media Twitter as much as 1000 data that later will be filtered to be 903 data because there are some data that has been duplicated. Researchers used the KNN, Decision Tree, and Naïve Bayes methods to compare the accuracy of the three methods. Researchers used the RapidMiner version 9.7.2 tools. The results showed that the sentiment analysis of Twitter data on BPJS services using the KNN method reached an accuracy level of 95.58% with class precision for pred. negative is 45.00%, pred. positive is 0.00%, and pred. neutral is 96.83%. Then the Decision Tree method the accuracy rate reaches 96.13% with the precision class for pred. negative is 55.00%, pred. positive is 0.00%, and pred. neutral is 97.28%. And the last one is the Naïve Bayes method which achieves 89.14% accuracy with precision class for pred. negative is 16.67%, pred. positive was 1.64%, and pred. neutral is 98.40%.

Penerapan Algoritma Naive Bayes Untuk Mengklasifikasi Pengaruh Negatif Game Online Bagi Remaja Milenial

In this modern era, the use of electronics such as cellphones, computers, laptops and others quite widely used for various needs. Information technology that is very developed today brings changes and affects social life. One of the problems in society is the large influence of online games because online games themselves have an attraction that makes people more fun playing than learning. It evidenced by the large number of millennial adolescents spending their daily time in front of computers or smartphones instead of books, and the lack of socializing is also one of the negative effects of playing online games and harms their health. To solve these problems, the classification method used is the naïve Bayes algorithm method, for classification in the form of online game user data as a whole, namely based on name, gender, age, number of days, duration and classification in the form of addiction and not addiction (normal). Therefore, this naïve Bayes algorithm can predict future opportunities based on past experiences. The results of the study of 100 online game user data in normal conditions were 78 respondents, and addiction was 22 respondents from the results of both concluded that the research results of millennial adolescents online game users were declared normal with an overall accuracy of 89.00%. Addicted recall class 77.27%, normal recall class 92.31%, addicted precision class 73.91%, normal precision class 93.51%.