Analisis Sentimen Ulasan Pengguna Aplikasi Layanan Kesehatan Digital Di Indonesia Menggunakan BERT Dan Support Vector Machine
DOI:
https://doi.org/10.61722/jssr.v4i6.13065Keywords:
Sentiment Analysis, IndoBERT, Support Vector Machine, TF-IDF, Digital Health ServiceAbstract
The development of digital health services in Indonesia has generated numerous user reviews that can be analyzed to identify user perceptions of service quality. This study aims to analyze the sentiment of user reviews of digital health service applications and compare the performance of BERT and Support Vector Machine (SVM). The dataset consisted of 13,456 reviews from Halodoc, Alodokter, and KlikDokter collected from 2022 to 2024. The research stages included data collection, preprocessing, sentiment labeling, classification, and model evaluation. IndoBERT was implemented through fine-tuning, while SVM used TF-IDF features with Grid Search optimization. The results showed that IndoBERT achieved an accuracy of 93.52% and a macro F1-score of 92.23%, while SVM achieved an accuracy of 87.14% and a macro F1-score of 84.71%. These results indicate that IndoBERT outperformed SVM in classifying sentiment in digital health service application reviews.
References
Amelia, A. A. (2024). Analisis Kepuasan Pengguna Atas Layanan Telemedicine Kesehatan Melalui Aplikasi Halodoc. Economics and Digital Business Review, 5(2), 879–886. https://doi.org/https://doi.org/10.37531/ecotal.v5i2.1300
Aryanti, F. A. D., Luthfiarta, A., & Soeroso, D. A. I. (2025). Aspect-Based Sentiment Analysis with LDA and IndoBERT Algorithm on Mental Health App: Riliv. Journal of Applied Informatics and Computing, 9(2), 361–375. https://doi.org/10.30871/jaic.v9i2.8958
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171–4186. Stroudsburg, PA, USA: Association for Computational Linguistics. https://doi.org/10.18653/v1/N19-1423
Hinonaung, J. S. H., Fatmawati, Y., Rambi, C. A., Ilmy, S. K., & Sari, F. N. (2023). Penerapan Analisis Sentimen Berbasis Aspek Menggunakan Mesin Vektor Pendukung pada Aplikasi Layanan Medis Digital. Journal of Comprehensive Science, 3(1), 1–15. https://doi.org/https://doi.org/10.59188/jcs.v3i1.3047
Kono, M. F., Fajri, I. N., & Pristyanto, Y. (2025). Public Sentiment Analysis on Corruption Issues in Indonesia Using IndoBERT Fine-Tuning, Logistic Regression, and Linear SVM. Journal of Applied Informatics and Computing, 9(5), 2616–2628. https://doi.org/10.30871/jaic.v9i5.10537
Lin, C.-H., & Nuha, U. (2023). Sentiment analysis of Indonesian datasets based on a hybrid deep-learning strategy. Journal of Big Data, 10(1), 88. https://doi.org/10.1186/s40537-023-00782-9
Medantoro, G. F. S., & Muljono, M. (2026). Comparative Analysis of IndoBERT and Classic Machine Learning Models for Sentiment Classification of Education Policy on Social Media X. Journal of Applied Informatics and Computing, 10(1), 548–557. https://doi.org/10.30871/jaic.v10i1.11723
Nugroho, K. S., Sukmadewa, A. Y., Wuswilahaken DW, H., Bachtiar, F. A., & Yudistira, N. (2021). BERT Fine-Tuning for Sentiment Analysis on Indonesian Mobile Apps Reviews. 6th International Conference on Sustainable Information Engineering and Technology 2021, 258–264. New York, NY, USA: ACM. https://doi.org/10.1145/3479645.3479679
Wongso, W., Setiawan, D. S., Limcorn, S., Joyoadikusumo, A., & Wales, S. (2023). NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural. Proceedings of ACL 2025 SEALP Workshop. https://doi.org/https://doi.org/10.18653/v1/2025.sealp-1.2
Downloads
Published
Issue
Section
License
Copyright (c) 2026 JOURNAL SAINS STUDENT RESEARCH
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
