Open AccessSentiment Analysis for Zoning System Admission Policy Using Support Vector Machine and Naive Bayes Methods
Author(s) -
Reynaldy Aries Ariyanto,
Nur Chamidah
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1776/1/012058
Subject(s) - zoning , naive bayes classifier , support vector machine , government (linguistics) , machine learning , artificial intelligence , sentiment analysis , computer science , literacy , quality (philosophy) , bayes' theorem , business , political science , law , bayesian probability , linguistics , philosophy , epistemology
Indonesia have low quality of education. According Trend International Mathematics and Science Study, Indonesian student’s mathematical literacy is ranked 36 from 49 countries. For Science literacy, Indonesia is ranked 35 from 49 countries. To increase quality of education in Indonesia, Indonesia’s government make a new policy for new student admission called zoning system. Zoning system is a new student admission according distance from house to school. Zoning system is new policy in Indonesia and there are still many pros and cons of the zoning system. Sentiment analysis is used to know whether Indonesia’s people agree or disagree about zoning system policy. In this study, we use supervised statistical learning methods that are Support Vector Machine (SVM) and Naïve Bayes for sentiment analysis of zoning system admission policy. The results show that Indonesia’s people tend to disagree with the zoning system admission policy because negative opinion is greater than positive opinion. Furthermore, accuracy rates of SVM and Naïve Bayes are 92.93% and 79.86% respectively. So, SVM is better than Naïve Bayes for sentiment analysis of zoning system admission policy.