PERBANDINGAN METODE SUPPORT VECTOR MACHINE KERNEL RBF DAN MULTINOMIAL NAÏVE BAYES PADA ANALISIS SENTIMEN KOMENTAR YOUTUBE BERDASARKAN KENAIKAN HARGA BAHAN BAKAR MINYAK DI INDONESIA

KUSUMA, OVA ARJUN (2024) PERBANDINGAN METODE SUPPORT VECTOR MACHINE KERNEL RBF DAN MULTINOMIAL NAÏVE BAYES PADA ANALISIS SENTIMEN KOMENTAR YOUTUBE BERDASARKAN KENAIKAN HARGA BAHAN BAKAR MINYAK DI INDONESIA. Other thesis, UPN Veteran Yogyakarta.

	Text ABSTRAK.pdf Download (10kB)
	Text Cover.pdf Download (253kB)
	Text DAFTAR ISI.pdf Download (1MB)
	Text DAFTAR PUSTAKA.pdf Download (807kB)
	Text Halaman Pengesahan Pembimbing.pdf Download (358kB)
	Text SKRIPSI FULL_ OVA ARJUN KUSUMA.pdf Restricted to Repository staff only Download (2MB)

Abstract

vi
ABSTRAK
Mengimplementasikan metode Support Vector Machine dengan kernel RBF dan
Naïve Bayes Multinomial untuk analisis sentiment dengan kelas negatif, netral, dan positif.
Serta mendapatkan perbandingan akurasi dari metode Support Vector Machine dengan
kernel RBF dan Naïve Bayes Multinomial dalam analisis sentimen. Berdasarkan penelitian
sebelumnya, penelitian ini memiliki perbedaan dimana secara spesifik membandingkan
performa metode SVM kernel RBF dan Multinomial Naïve Bayes. Serta menggunakan
komentar YouTube mengenai kenaikan BBM di Indonesia sebagai dataset.
Penelitian yang telah dilakukan menggunakan 1500 komentar mengenai kenaikan
BBM di Indonesia sebagai dataset. kemudian menggunakan metode confusion matrix untuk
evaluasi kinerja model, menunjukkan metode Support Vector Machine (SVM) kernel RBF
(Radial Basis Function) menghasilkan nilai akurasi sebesar 65.4%, presisi sebesar 63.7%,
recall sebesar 59.4%, f1-score sebesar 59.8%. Sedangkan metode Multinomial Naïve Bayes
dengan nilai akurasi sebesar 63.8%, presisi sebesar 60.4%, recall sebesar 57.7%, f1-score
sebesar 56.6%. Berdasarkan hasil evaluasi, metode Support Vector Machine dengan kernel
RBF lebih unggul dibandingkan metode Multinomial Naïve Bayes.
Kata kunci: Analisis Sentimen, Support Vector Machine (SVM), Kernel Radial Basis
Function (RBF), Multinomial Naive Bayes, Komentar YouTube, Kenaikan harga bahan
bakar
vii
ABSTRACT
To implement the Support Vector Machine method with an RBF kernel and
Multinomial Naïve Bayes for sentiment analysis with negative, neutral, and positive classes.
Additionally, to compare the accuracy of the Support Vector Machine with an RBF kernel
and Multinomial Naïve Bayes in sentiment analysis. Based on previous research, this study
differs by specifically comparing the performance of the SVM with RBF kernel and the
Multinomial Naïve Bayes methods. Additionally, it uses YouTube comments on the fuel price
increase in Indonesia as the dataset.
The study utilized 1500 comments regarding the increase in fuel prices in Indonesia
as the dataset. The evaluation of model performance was conducted using the confusion
matrix method, showing that the Support Vector Machine (SVM) with the Radial Basis
Function (RBF) kernel achieved an accuracy of 65.4%, precision of 63.7%, recall of 59.4%,
and an F1-score of 59.8%. Meanwhile, the Multinomial Naïve Bayes method resulted in an
accuracy of 63.8%, precision of 60.4%, recall of 57.7%, and an F1-score of 56.6%. Based
on the evaluation results, the Support Vector Machine with the RBF kernel outperformed
the Multinomial Naïve Bayes method.
Keywords: Sentiment Analysis,Support Vector Machine (SVM), Radial Basis Function
(RBF) Kernel, Multinomial Naive Bayes, YouTube Comments, Fuel Price Increase

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Sentiment Analysis,Support Vector Machine (SVM), Radial Basis Function (RBF) Kernel, Multinomial Naive Bayes, YouTube Comments, Fuel Price Increase
Subjects:	Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions:	Faculty of Engineering, Science and Mathematics > School of Chemistry
Depositing User:	Eko Yuli
Date Deposited:	07 Nov 2024 03:46
Last Modified:	07 Nov 2024 03:46
URI:	http://eprints.upnyk.ac.id/id/eprint/41589

Actions (login required)

View Item