COMPARATIVE SENTIMENT ANALYSIS OF OSS INDONESIA REVIEWS FOR DIGITAL ECONOMY USING SVM AND NAIVE BAYES
Keywords:
Sentiment Analysis, OSS Indonesia, Support Vector Machine, Naive Bayes, Digital Government ServicesAbstract
The rapid growth of Indonesia’s digital economy has increased the importance of effective government digital services, particularly for micro, small, and medium enterprises (MSMEs). The Online Single Submission (OSS) Indonesia application was developed to simplify business licensing processes; however, user reviews indicate persistent usability and system performance issues. This study aims to analyze user sentiment toward the OSS Indonesia application and compare the performance of Support Vector Machine (SVM) and Naive Bayes algorithms in classifying sentiment from Google Play Store reviews. A total of 2,208 Indonesian-language reviews collected between 2021 and 2025 were manually labeled into positive and negative categories by three annotators, achieving a Fleiss’ Kappa score of 0.95. Text preprocessing and TF-IDF feature extraction were applied, followed by model evaluation using three train test split scenarios (70:30, 80:20, and 90:10). The results show that SVM consistently outperformed Naive Bayes across all evaluation metrics, achieving the best performance with an 80:20 split (accuracy 0.94 and F1-score 0.95). While Naive Bayes demonstrated higher recall, SVM provided a more balanced and reliable classification. These findings indicate that SVM is more suitable for sentiment analysis of Indonesian government digital service reviews and highlight the importance of user feedback in improving public digital platforms.
Downloads
References
Aufar, A. F., Rosid, M. A., Eviyanti, A., & Astutik, I. R. I. (2023). Optimizing Text Preprocessing for Accurate Sentiment Analysis on E-Wallet Reviews: Mengoptimalkan Preprocessing Teks untuk Analisis Sentimen yang Akurat pada Ulasan E-Wallet. JICTE (Journal of Information and Computer Technology Education), 7(2), 42–50. https://doi.org/10.21070/jicte.v7i2.1650
Chen, H., Hu, S., Hua, R., & Zhao, X. (2021). Improved naive Bayes classification algorithm for traffic risk management. EURASIP Journal on Advances in Signal Processing, 2021(1), 30-. https://doi.org/10.1186/s13634-021-00742-6
Fransiscus, & Girsang, A. S. (2022, December 31). Sentiment Analysis of COVID-19 Public Activity Restriction (PPKM) Impact using BERT Method. arXiv.Org. https://arxiv.org/abs/2301.00096
Google Play Store. (2025). OSS Indonesia application. Google Play Store. https://play.google.com/store/apps/details?id=id.go.oss
Lindén, K., Jauhiainen, T., & Hardwick, S. (2023). FinnSentiment: A Finnish social media corpus for sentiment polarity annotation. Language Resources and Evaluation, 57(2), 581–609. https://doi.org/10.1007/s10579-023-09644-5
Moons, F., & Vandervieren, E. (2023, March 22). Measuring agreement among several raters classifying subjects into one or more (hierarchical) categories: A generalization of Fleiss’ kappa. arXiv.Org. https://arxiv.org/abs/2303.12502
Palomino, M. A., & Aider, F. (2022). Evaluating the effectiveness of text pre-processing in sentiment analysis. Applied Sciences, 12(17). https://doi.org/10.3390/app12178765
Prasetyo, Y. A., Utami, E., & Yaqin, A. (2024). Pengaruh Komposisi Split Data Terhadap Performa Akurasi Analisis Sentimen Algoritma Naïve Bayes dan SVM. Journal of Electrical Engineering and Computer (JEECOM), 6(2), 382–390. https://doi.org/10.33650/jeecom.v6i2.9188
Rahmatullah, A., & Annisa, Q. (2025). Application of TF-IDF and Word2vec for feature extraction in sentiment analysis of free nutritious food policies. Journal of Computer Electronic and Telecommunication, 6(2). https://doi.org/10.52435/complete.v6i2.741
Rahmatullah, A., & Annisa, Q. (2026). Application of TF-IDF and Word2vec for feature extraction in sentiment analysis of free nutritious food policies. Journal of Computer Electronic and Telecommunication, 6(2). https://doi.org/10.52435/complete.v6i2.741
Ramadila, H., Syafitri, E. D., & Zamsuri, A. (2025). Sentiment detection of Shopee e-commerce application reviews using natural language processing and support vector machine. JAISEN: Journal of Advanced Information Systems and Engineering, 1(1), 28–38.
Restiani, Y., & Purwadi, J. (2024). Support vector machine for classification: a mathematical and scientific approach in data analysis. Jurnal Penelitian Pendidikan IPA, 10(11), 9896–9903. https://doi.org/10.29303/jppipa.v10i11.8122
Sandy, M., & Laple Satria Putra, R. (2025). View of analisis sentimen komentar pengguna aplikasi Segari di Google Playstrore menggunakan metode Support Vector Machine (SVM). Jurnal Multimedia Dan Teknologi Informasi, 07(03), 642–652.
Saputra, B. (2025, July 31). Minister projects digital sector’s eight-percent contribution to GDP. ANTARA. https://en.antaranews.com/news/370173/minister-projects-digital-sectors-eight-percent-contribution-to-gdp
Sultan, R., Junus, N., & Elfrikri, N. F. (2025). Legal protection of MSME trademarks as a pillar of local economic justice. YUDHISTIRA : Jurnal Yurisprudensi, Hukum Dan Peradilan, 3(1), 55–65. https://doi.org/10.59966/yudhistira.v3i1.1776
Syah, F. P., Hasanuddin, T., & Kurniati, nia. (2025). Implementasi Naive Bayes Untuk Analisis Sentimen Pada data Twitter Tentang Isu Politik di Indonesia. LINIER: Literatur Informatika Dan Komputer, 2(3), 302–316. https://doi.org/10.33096/linier.v2i3.3142
Yuliani, S. P., Muharani, A. A. P., Fatmawati, R. Q., & Fahmi, F. (2025). Sentiment Analysis in User Reviews of Gojek Application using Natural Language Processing. Journal of System and Computer Engineering (JSCE), 6(4), 296–305. https://doi.org/10.61628/jsce.v6i4.2062
Download Journal Template 
