Classification Of Sentiments On Social Security Implementing Agency (BPJS) On Twitter Social Media Using Naive Bayes
##plugins.themes.bootstrap3.article.sidebar##
##plugins.themes.bootstrap3.article.main##
Abstract
BPJS Kesehatan is listed as the agency that provides insurance financial services with the largest number of public complaints in the Ombudsman in 2019. The number of complaints on the official BPJS Kesehatan twitter account can be an indication of the level of satisfaction and public sentiment towards BPJS Kesehatan services. Twitter can be used to convey the experiences, ideas, complaints, opinions, or facts presented. The Tweet can be either a positive or a negative opinion. To find out, there needs to be an existing data processing process, so that it can be classified as a positive and a negative opinion. The classification method used in this study is the Naive Bayes Classifier. This study aims to see the tendency of the public towards BPJS Kesehatan based on sentiment classifications and to see the level of accuracy of the Naive Bayes Classifier method in classifying BPJS Kesehatan sentiments on Twitter social media. The data used were 780 tweet data from March to May 2020. The results of model testing using the Confusion Matrix resulted in an accurate performance of 86.25%, precision of 84.92%, recall of 87.78%, and f-measure of 86, 37%. As well as the results of testing the data in May 2020, there were 52% of tweets in the positive sentiment category, and 48% of tweets in the negative category
##plugins.themes.bootstrap3.article.details##
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
The writer agreed that the article copyright by Smatika journal and the writer has the right to disseminate the paper published without permission in advance.
[2] Rish, I. (2006). An Empirical Study of The Naive Bayes Classifier. International Joint Conference on Artificial Intellegence, 41-46
[3] Aliandu, P. (2013). Twitter Used by Indonesian President: An Sentiment Analysis of Timeline. Information Systems International Conference, 713-716.
[4] Falahah & Nur, D. D. A. (2015). Pengembangan Aplikasi Sentiment Analysis Menggunakan Metode Naïve Bayes. Seminar Nasional Sistem Informasi Indonesia, 335-340.
[5] Liu, B. (2010). Handbook of Natural Lenguage Processing 2nd Edition. Boca Raton: CRC Press.
[6] Abdan, S. (2017). Analisis Sentimen Masyarakat Terhadap E-Commerce Pada Media Sosial Menggunakan Metode Naive Bayes Classifier (NBC) Dengan Seleksi Fitur Information Gain (IG). Malang: Universitas Islam Negeri Maulana Malik Ibrahim.
[7] Taufik, K. (2017). Implementasi Text Mining Pada Analisis Sentimen Pengguna Twitter Terhadap Media Mainstream Menggunakan Naive Bayes Classifier Dan Support Vector Machine. Surabaya: Institut Teknologi Sepuluh Nopember.