Vol. 3 No. 2 (2026) • Articles
Open Access

Perbandingan Ketahanan Lintas-Domain Indobert dan SVM Pada Ulasan Game dan Media Sosial Berbahasa Indonesia

Dyo Arya Purnama
Sriwijaya University image/svg+xml
Alsella Meiriza
Sriwijaya University image/svg+xml
Hardini Novianti
Sriwijaya University image/svg+xml
Rizka Dhini Kurnia
Sriwijaya University image/svg+xml
Ken Ditha Tania
Sriwijaya University image/svg+xml
Published: November 25, 2026 Pages: 582-593
Original Full-Text Article
Download published version for reading and archiving
Abstract

Sentiment classifiers for Indonesian app reviews are rarely tested on any app other than the one that provided their training data. This study contrasts a linear support vector machine (SVM) with TF-IDF features and a fine-tuned IndoBERT. Both models were trained on Roblox reviews and then tested on held-out Roblox reviews as well as on Minecraft and TikTok reviews from Google Play. Each app contributed 2,500 class-balanced reviews, with labels derived from ratings. Performance was measured by macro-F1 with 95% bootstrap confidence intervals, and domain distance was assessed using five measures. On Roblox itself, IndoBERT and SVM showed no clear difference (0.867 vs 0.850). Across domains, IndoBERT scored roughly 0.065 higher and lost about 0.048 less. TikTok lay farther from Roblox on every distance measure and suffered larger drops, which is consistent with a distance effect. Domain-adaptive pretraining reduced the TikTok drop by 0.020 (macro-F1 rose from 0.794 to 0.810) but had no effect on Minecraft. In practical terms, IndoBERT is the safer option for developers who apply a classifier to other apps, while SVM is enough as a cheap in-domain baseline.

Article Metrics & Downloads Graph
Monthly Download Trends:
Author Biographies
Dyo Arya Purnama Sriwijaya University

Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.

Alsella Meiriza Sriwijaya University

Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.

Hardini Novianti Sriwijaya University

Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.

Rizka Dhini Kurnia Sriwijaya University

Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.

Ken Ditha Tania Sriwijaya University

Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.

How to Cite
Purnama, D. A., Meiriza, A. ., Novianti, H., Kurnia, R. D., & Tania, K. D. (2026). Perbandingan Ketahanan Lintas-Domain Indobert dan SVM Pada Ulasan Game dan Media Sosial Berbahasa Indonesia. Jurnal Manajemen Dan Teknologi, 3(2), 582-593. https://doi.org/10.63447/jmt.v3i2.2197
License

This work is licensed under a Copyright (c) 2026 Dyo Arya Purnama, Alsella Meiriza, Hardini Novianti, Rizka Dhini Kurnia, Ken Ditha Tania .

Creative Commons Attribution 4.0 International License (CC BY 4.0)

This is an open-access article distributed under the terms of the Creative Commons Attribution 4.0 International License .

  • Share: You are free to copy, distribute, and transmit the work in any medium or format.
  • Adapt: You are free to remix, transform, and build upon the work for any purpose, even commercially.
  • Attribution: You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
Copyright & Retention: Authors retain copyright without restrictions and grant this journal the right of first publication under an open-access model. The journal retains non-exclusive publishing rights for archiving, indexing, and scholarly dissemination.

References
Total: 19 References
  1. Agro, M. T., & Aldarmaki, H. (2023). Handling realistic label noise in BERT text classification. Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP), 11–20. https://doi.org/10.48550/arXiv.2305.16337.
  2. Athyabunnaja, S., Tamrin, T., & Mulyo, H. (2026). Implementation of IndoBERT for text-based emotion classification on TikTok application reviews in Google Play Store. Journal Dinda: Data Science, Information Technology, and Data Analytics, 6(1), 18–24. https://doi.org/10.20895/dinda.v6i1.10174.
  3. Calderon, N., Porat, N., Ben-David, E., Chapanin, A., Gekhman, Z., Oved, N., Shalumov, V., & Reichart, R. (2024). Measuring the robustness of NLP models to domain shifts. Findings of the Association for Computational Linguistics: EMNLP 2024, 126–154. https://doi.org/10.18653/v1/2024.findings-emnlp.7.
  4. 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, 1, 4171–4186. https://doi.org/10.18653/v1/N19-1423.
  5. Du, W. (2025). When +1% is not enough: A paired bootstrap protocol for evaluating small improvements [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2511.19794.
  6. Hidayatullah, A. F., Apong, R. A., Lai, D. T. C., & Qazi, A. (2023). Corpus creation and language identification for code-mixed Indonesian-Javanese-English tweets. PeerJ Computer Science, 9, Article e1312. https://doi.org/10.7717/peerj-cs.1312.
  7. Imaduddin, H., A'la, F. Y., & Nugroho, Y. S. (2023). Sentiment analysis in Indonesian healthcare applications using IndoBERT approach. International Journal of Advanced Computer Science and Applications, 14(8). https://doi.org/10.14569/IJACSA.2023.0140813.
  8. Malik, B., Kashyap, A. R., Kan, M.-Y., & Poria, S. (2023). UDAPTER – Efficient domain adaptation using adapters. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, 2249–2263. https://doi.org/10.18653/v1/2023.eacl-main.165.
  9. Opitz, J. (2024). A closer look at classification evaluation metrics and a critical reflection of common evaluation practice. Transactions of the Association for Computational Linguistics, 12, 820–836. https://doi.org/10.1162/tacl_a_00675.
  10. Rostami, M., Bose, D., Narayanan, S., & Galstyan, A. (2023). Domain adaptation for sentiment analysis using robust internal representations. Findings of the Association for Computational Linguistics: EMNLP 2023, 11484–11498. https://doi.org/10.18653/v1/2023.findings-emnlp.769.
  11. Sabiri, B., Khtira, A., El Asri, B., & Rhanoui, M. (2023). Analyzing BERT's performance compared to traditional text classification models. Proceedings of the 25th International Conference on Enterprise Information Systems (ICEIS), 1, 572–582. https://doi.org/10.5220/0011983100003467.
  12. Setiawan, B. (2024). A review of sentiment analysis applications in Indonesia between 2023–2024. JIEET (Journal of Information Engineering and Educational Technology), 8(2), 71–83. https://doi.org/10.26740/jieet.v8n2.p71-83.
  13. Shollis, R. F., & Sanjaya, U. P. (2026). Comparison of LinearSVC and complement naive Bayes on Coretax sentiment analysis using IndoBERT pseudo-labeling and ADASYN. JIKO (Jurnal Informatika dan Komputer), 9(2). https://doi.org/10.33387/jiko.v9i2.11615.
  14. Sunan, M., Resiloy, U. D. A., Endriani, D., Suhaeni, C., Sartono, B., & Dito, G. A. (2026). IndoBERT optimization for sentiment analysis on DeepSeek app reviews. IJCCS (Indonesian Journal of Computing and Cybernetics Systems), 20(1), 95–106. https://doi.org/10.22146/ijccs.107507.
  15. Wahid, Y. A., Sanatang, & Andayani, D. D. (2025). Performance comparison of SVM and Naïve Bayes for Indonesian-language sentiment analysis on Free Fire reviews using TF-IDF and SMOTE. JESSI, 6(4). https://doi.org/10.59562/jessi.v6i4.10818.
  16. Xie, Y., Aggarwal, K., & Ahmad, A. (2024). Efficient continual pre-training for building domain specific large language models. Findings of the Association for Computational Linguistics: ACL 2024, 10184–10201. https://doi.org/10.18653/v1/2024.findings-acl.606.
  17. Zahra, N. Z., Farhanatussaidah, S., Afifah, N. N., Muthoharoh, L., Satria, A., & Manullang, M. C. T. (2026). Benchmarking logistic regression, SVM, naive Bayes, and IndoBERT fine-tuning for sentiment analysis on Indonesian product reviews [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2605.03439.
  18. Zaidan, M. N., Sibaroni, Y., & Prasetiyowati, S. S. (2024). Learning rate and epoch optimization in the fine-tuning process for IndoBERT's performance on sentiment analysis of MyTelkomsel app reviews. Jurnal Teknik Informatika (JUTIF), 5(5), 1443–1450. https://doi.org/10.52436/1.jutif.2024.5.5.2396.
  19. Zuhir, N., Salim, A. M., Premkumar, P., & Farazi, M. (2025). Beyond stars: Bridging the gap between ratings and review sentiment with LLM [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2509.20953.
Similar Articles

Articles sharing related keywords and machine learning classifications:

Klasifikasi Kualitas Karet Menggunakan Metode Random Forest Pada Perusahaan XYZ
Pengaruh Ulasan Pelanggan Online dan Persepsi Harga terhadap Niat Beli Konsumen Sudut Kedai di Metland Transyogi
Kepatuhan Masa Simpan Data KIA dan Aksesibilitas Data PMB
Membangun Keunggulan Kompetitif melalui Platform E-Commerce: Studi Kasus Tokopedia
Strategi Pengembangan Laboratorium Simulasi Bisnis Menuju Smart Campus Guna Meningkatkan Work Readiness Politeknik Negeri Bengkalis
Most read articles by the same author(s)

Other papers published by author(s) in this journal:

Klasterisasi Karakteristik Pengguna E-Commerce Berdasarkan Profil Pengguna Menggunakan Algoritma K-Prototypes
Klasifikasi Kualitas Karet Menggunakan Metode Random Forest Pada Perusahaan XYZ
Perbandingan IndoBERT dan mBERT Untuk Klasifikasi Toksisitas Pada Chat Roblox dan Minecraft Berbahasa Indonesia