ANALISA SENTIMEN PENGGUNA TERHADAP KEBIJAKAN BARU WHATSAPP MENGGUNAKAN NAIVE BAYES CLASSIFIER DAN SUPPORT VECTOR MACHINE
No Thumbnail Available
Date
2021-12
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Elfitra
Abstract
This study applies the Naïve Bayes Classifier (NBC) and Support Vector Machine (SVM)
algorithms in classifying WhatsApp user review data to determine the percentage of user
sentiment towards the whatsapp’s new privacy policy and to compare the performance of
the two algorithms. This study uses 760 data with the distribution of training and testing
data, namely 90%:10%, 70%:30%, 50%:50%, 30%:70%, and 10%:90%. The results
showed that there were 338 positive reviews and 422 negative reviews, so it can be
concluded that the trend of user sentiment towards the whatsapp’s new privacy policy
was negative with a percentage of 56%. The results of the confusion matrix test show that
the highest accuracy value is obtained in the first test with a data ratio of 90%:10%. The
NBC method has an accuracy of 92.11% while the SVM method has an accuracy of
96.05%, it can be said that the SVM method has a better performance than the NBC
method in classifying whatsapp user review data.
Description
Keywords
Sentiment Analysis, New Privacy Policy, Naïve Bayes Classifier, Support Vector Machine, Whatsapp
Citation
Perpustakaan