Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews

This study aims to evaluate and compare the performance of three machine learning algorithms—Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), and Naïve Bayes—for sentiment classification of user reviews on the NU Online application in the Google Play Store. NU Online is a religious digital...

Full description

Saved in:
Bibliographic Details
Main Authors: Heti Aprilianti, Khothibul Umam, Maya Rini Handayani
Format: Article
Language:English
Published: Politeknik Negeri Batam 2025-06-01
Series:Journal of Applied Informatics and Computing
Subjects:
Online Access:https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9482
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849410860322127872
author Heti Aprilianti
Khothibul Umam
Maya Rini Handayani
author_facet Heti Aprilianti
Khothibul Umam
Maya Rini Handayani
author_sort Heti Aprilianti
collection DOAJ
description This study aims to evaluate and compare the performance of three machine learning algorithms—Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), and Naïve Bayes—for sentiment classification of user reviews on the NU Online application in the Google Play Store. NU Online is a religious digital platform providing Islamic content such as articles, prayers, and worship schedules. A total of 1,500 user reviews were collected using web scraping, and 1,491 were retained after data cleaning. Preprocessing steps included punctuation removal, case folding, normalization, stopword removal, stemming, and tokenization. Sentiment labels (positive or negative) were automatically assigned using a lexicon-based approach. The performance of the models was assessed using accuracy, precision, recall, and F1-score, calculated via confusion matrix with a training-testing data split. The results show that the SVM with a linear kernel achieved the best accuracy (81.6%), followed by Naïve Bayes (73.2%) and K-NN (66.9%). These findings indicate that SVM is the most effective algorithm in this context, providing practical contributions for developers of the NU Online digital religious platform and contributing to research in Indonesian natural language processing.
format Article
id doaj-art-8d056ff91978450eb7ade66534dfd01f
institution Kabale University
issn 2548-6861
language English
publishDate 2025-06-01
publisher Politeknik Negeri Batam
record_format Article
series Journal of Applied Informatics and Computing
spelling doaj-art-8d056ff91978450eb7ade66534dfd01f2025-08-20T03:34:57ZengPoliteknik Negeri BatamJournal of Applied Informatics and Computing2548-68612025-06-019392092710.30871/jaic.v9i3.94827027Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application ReviewsHeti Aprilianti0Khothibul Umam1Maya Rini Handayani2Teknologi Informasi, Fakultas Sains dan Teknologi, UIN Walisongo SemarangTeknologi Informasi, Fakultas Sains dan Teknologi, UIN Walisongo SemarangTeknologi Informasi, Fakultas Sains dan Teknologi, UIN Walisongo SemarangThis study aims to evaluate and compare the performance of three machine learning algorithms—Support Vector Machine (SVM), K-Nearest Neighbors (K-NN), and Naïve Bayes—for sentiment classification of user reviews on the NU Online application in the Google Play Store. NU Online is a religious digital platform providing Islamic content such as articles, prayers, and worship schedules. A total of 1,500 user reviews were collected using web scraping, and 1,491 were retained after data cleaning. Preprocessing steps included punctuation removal, case folding, normalization, stopword removal, stemming, and tokenization. Sentiment labels (positive or negative) were automatically assigned using a lexicon-based approach. The performance of the models was assessed using accuracy, precision, recall, and F1-score, calculated via confusion matrix with a training-testing data split. The results show that the SVM with a linear kernel achieved the best accuracy (81.6%), followed by Naïve Bayes (73.2%) and K-NN (66.9%). These findings indicate that SVM is the most effective algorithm in this context, providing practical contributions for developers of the NU Online digital religious platform and contributing to research in Indonesian natural language processing.https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9482sentiment analysissupport vector machine (svm)nu onlineuser reviewsclassification algorithms
spellingShingle Heti Aprilianti
Khothibul Umam
Maya Rini Handayani
Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews
Journal of Applied Informatics and Computing
sentiment analysis
support vector machine (svm)
nu online
user reviews
classification algorithms
title Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews
title_full Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews
title_fullStr Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews
title_full_unstemmed Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews
title_short Comparative Study of SVM, KNN, and Naïve Bayes for Sentiment Analysis of Religious Application Reviews
title_sort comparative study of svm knn and naive bayes for sentiment analysis of religious application reviews
topic sentiment analysis
support vector machine (svm)
nu online
user reviews
classification algorithms
url https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9482
work_keys_str_mv AT hetiaprilianti comparativestudyofsvmknnandnaivebayesforsentimentanalysisofreligiousapplicationreviews
AT khothibulumam comparativestudyofsvmknnandnaivebayesforsentimentanalysisofreligiousapplicationreviews
AT mayarinihandayani comparativestudyofsvmknnandnaivebayesforsentimentanalysisofreligiousapplicationreviews