Perbandingan IndoBERT dan mBERT Untuk Klasifikasi Toksisitas Pada Chat Roblox dan Minecraft Berbahasa Indonesia
Original Full-Text Article
Download published version for reading and archivingAbstract
Toxic chat in online games exposes young players to harassment, while moderation of Indonesian chat is hampered by slang and non-standard spelling. This study compares monolingual IndoBERT and multilingual mBERT for four-class toxicity classification (neutral, violence, racist, harassment) of Indonesian Roblox and Minecraft chat to identify the more suitable model for moderation. Both models were fine-tuned with identical settings on the Indonesian Chat Dataset (10,702 chats) using three seeds, and evaluated with accuracy, macro-averaged precision, recall, F1-score, and McNemar’s test. IndoBERT reached a mean macro F1-score of 0.8541 ± 0.0019 versus 0.8263 ± 0.0090 for mBERT, significant in two of three seeds. Neutral was the hardest class, and IndoBERT let 5.8% of toxic chats pass as neutral versus 8.3% for mBERT. Excluding 106 duplicated test chats did not change the ranking. Under these settings, IndoBERT performed better, although labels lack inter-annotator agreement and data cover two games only.
Author Biographies
Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.
Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.
Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.
Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.
Program Studi Sistem Informasi, Fakultas Ilmu Komputer, Universitas Sriwijaya, Kota Palembang, Provinsi Sumatera Selatan, Indonesia.
How to Cite
This work is licensed under a Copyright (c) 2026 Idris Sonny, Allsela Meiriza, Hardini Novianti, Mira Afriani, Rizka Dhina Kurnia .
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.
References
Total: 20 References- Dharmawan, S., Mawardi, V. C., & Perdana, N. J. (2023). Klasifikasi ujaran kebencian menggunakan metode feedforward neural network (IndoBERT). Jurnal Ilmu Komputer dan Sistem Informasi, 11(1). https://doi.org/10.24912/jiksi.v11i1.24066.
- Ghosh, K., & Senapati, A. (2025). Hate speech detection in low-resourced Indian languages: An analysis of transformer-based monolingual and multilingual models with cross-lingual experiments. Natural Language Processing, 31(2), 393–414. https://doi.org/10.1017/nlp.2024.28.
- Hakim, A. N., Sibaroni, Y., & Prasetyowati, S. S. (2024). Detection of hate-speech text on Indonesian Twitter social media using IndoBERTweet-BiLSTM-CNN. In 2024 12th International Conference on Information and Communication Technology (ICoICT) (pp. 374–381). IEEE. https://doi.org/10.1109/ICoICT61617.2024.10698615.
- Hibatullah, H., Ballı, T., & Yetkin, E. F. (2025). Verbal harassment detection in online games using machine learning methods. Entertainment Computing, Article 101009. https://doi.org/10.1016/j.entcom.2025.101009.
- Ibrohim, M. O., & Budi, I. (2023). Hate speech and abusive language detection in Indonesian social media: Progress and challenges. Heliyon, 9(8), Article e18647. https://doi.org/10.1016/j.heliyon.2023.e18647.
Similar Articles
Articles sharing related keywords and machine learning classifications:
Most read articles by the same author(s)
Other papers published by author(s) in this journal: