Enhancing Javanese Emotion Classification: A Comparative Study of Cross-Lingual, Supervised, and Hybrid Transfer Learning using IndoBERTweet
DOI:
https://doi.org/10.63158/journalisi.v8i3.1657Keywords:
Emotion classification, Javanese Ngoko, cross-lingual transfer learning, IndoBERTweet, machine translationAbstract
This research investigates transfer learning efficacy for five-class emotion classification in Javanese Ngoko. A parallel Indonesian–Javanese Ngoko corpus was synthesized by translating 5,400 samples from the PRDECT-ID dataset using machine translation, with translation quality verified via a preliminary expert validation sample. Using IndoBERTweet as the backbone architecture, three paradigms were evaluated: zero-shot transfer (E1), fully supervised learning (E2), and cross-lingual transfer learning (E3) with identical hyperparameters. Empirical results indicate that the cross-lingual transfer (E3) setup achieved peak performance (67,5% accuracy; 0,67 weighted F1) under the evaluated dataset and experimental setting. Per-class analysis identified that positive affect (Happy) showed cross-lingual stability, whereas negative emotions (Sadness, Fear) suffered degradation due to lexical divergence between the two languages. Training dynamics revealed early-onset overfitting, suggesting model capacity exceeds current dataset density. This work establishes a baseline benchmark for Javanese emotion classification and provides a reproducible machine-translated parallel corpus, emphasizing the need for future validation with native-speaker data to mitigate translation bias.
Downloads
References
[1] Z. Maryani, R. Legino, and P. Waijittragum, “Linguistic hybridity between Javanese and Bahasa Indonesia in contemporary Javanese songs,” vol. 23, no. 2, pp. 278–286, 2025.
[2] Hermanto and T. W. Sen, “Syllable-Based Javanese Speech Recognition Using MFCC and CNNs : Noise Impact Evaluation,” J. Tek. Inform., vol. 18, no. 1, pp. 32–42, 2025, doi: 10.15408/jti.v18i1.41067.
[3] A. F. Hidayatullah, R. A. Apong, D. T. C. Lai, and A. Qazi, “Word Level Language Identification in Indonesian-Javanese-English Code-Mixed Text,” Procedia Comput. Sci., vol. 244, pp. 105–112, 2024, doi: 10.1016/j.procs.2024.10.183.
[4] S. R. Ntou, “Exploring complex diglossia in Javanese society,” Cogent Arts Humanit., vol. 11, no. 1, p., 2024, doi: 10.1080/23311983.2024.2313286.
[5] W. Udasmoro, A. Firmonasari, and W. T. Astuti, “Access to and Usage of Javanese in Mass Media among Yogyakarta Youth,” vol. 23, no. 2, pp. 268–277, 2023, doi: 10.24071/joll.v23i2.5508.
[6] P. Triawan, I. Tahyudin, and P. Purwadi, “Impact of NLP Algorithms on Sentiment Analysis Efficiency and Accuracy,” J. Inf. Syst. Informatics, vol. 7, no. 3, pp. 2684–2709, 2025, doi: 10.51519/journalisi.v7i3.1222.
[7] F. Arifin, A. Nasuha, A. S. Priambodo, A. Winursito, and T. S. Gunawan, “Advanced Multimodal Emotion Recognition for Javanese Language Using Deep Learning,” Indones. J. Electr. Eng. Informatics, vol. 12, no. 3, pp. 503–515, 2024, doi: 10.52549/ijeei.v12i3.5662.
[8] S. Praveena, “Emotion Classification Using BERT : A Comprehensive Study,” Tuijin Jishu/Journal Propuls. Technol., vol. 45, no. 4, pp. 3337–3345, 2024.
[9] A. Alabd-aljabar, Z. Raisan, M. Adnan, and S. Dhou, “A Hybrid Transfer Learning Approach to Teeth Diagnosis Using Orthopantomogram Radiographs,” IEEE Access, vol. 12, no. December, pp. 178142–178152, 2024, doi: 10.1109/ACCESS.2024.3507925.
[10] A. M. H. Pardede, R. Winanjaya, and J. Ismail, “HYBRID TRANSFER LEARNING AND ADVANCED DATA AUGMENTATION FOR MULTICLASS BRAIN TUMOR CLASSIFICATION,” vol. 11, no. 3, pp. 669–679, 2026, doi: 10.33480/jitk.v11i3.7524.
[11] T. Sindane, V. Marivate, and A. Modupe, “Cross-lingual embedding methods and applications : A systematic review for low-resourced scenarios,” Nat. Lang. Process. J., vol. 12, no. October 2024, p. 100157, 2025, doi: 10.1016/j.nlp.2025.100157.
[12] J. F. Kusuma and A. Chowanda, “Indonesian Hate Speech Detection Using IndoBERTweet and BiLSTM on Twitter,” Int. J. INFORMATICS Vis., vol. 7, no. September, pp. 773–780, 2023, doi: 10.30630/joiv.7.3.1035.
[13] A. I. Gufroni, P. Purwanto, and F. Farikhin, “Academic Performance Prediction Using Supervised Learning Algorithms in University Admission,” JOIV Int. J. Informatics Vis., vol. 9, no. January, pp. 184–194, 2025, doi: 10.62527/joiv.9.1.2974.
[14] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” COLING 2020 - 28th Int. Conf. Comput. Linguist. Proc. Conf., pp. 757–770, 2020, doi: 10.18653/v1/2020.coling-main.66.
[15] F. Koto Jey Han Lau Timothy Baldwin, “INDOBERTWEET: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization,” pp. 10660–10668, 2021.
[16] A. F. Hidayatullah, R. A. Apong, D. T. C. Lai, and A. Qazi, “Corpus creation and language identification for code-mixed Indonesian-Javanese-English Tweets,” PeerJ Comput. Sci., vol. 9, pp. 1–24, 2023, doi: 10.7717/PEERJ-CS.1312.
[17] G. Enrique, I. Alfina, and E. Yulianti, “Javanese part-of-speech tagging using cross-lingual transfer learning,” IAES Int. J. Artif. Intell., vol. 13, no. 3, pp. 3498–3509, 2024, doi: 10.11591/ijai.v13.i3.pp3498-3509.
[18] P. K. L. Utama, J. S. Dibangoye, and T. M. Tashu, “Cross-Lingual Emotion Recognition in Balinese Text using Multilingual-LLMs under Peer-Collaborations Settings,” in Proceedings of the Second Workshop on Language Models for Low-Resource Languages (LoResLM 2026), 2026, pp. 225–238. doi: 10.18653/v1/2026.loreslm-1.21.
[19] R. Sutoyo, S. Achmad, A. Chowanda, E. W. Andangsari, and S. M. Isa, “PRDECT-ID: Indonesian product reviews dataset for emotions classification tasks,” Data Br., vol. 44, p. 108554, 2022, doi: 10.1016/j.dib.2022.108554.
[20] T. O. Tafa, S. Zaiton, M. Hashim, and M. S. Othman, “Machine Translation Performance for Low-Resource Languages : A Systematic Literature Review,” IEEE Access, vol. 13, no. March, pp. 72486–72505, 2025, doi: 10.1109/ACCESS.2025.3562918.
[21] T. R. Mahesh, V. K. V, D. K. V, O. Geman, and M. Margala, “Healthcare Analytics The stratified K-folds cross-validation and class-balancing methods with high-performance ensemble classifiers for breast cancer classification,” Healthc. Anal., vol. 4, no. July, p. 100247, 2023, doi: 10.1016/j.health.2023.100247.
[22] M. Martianus, D. Christian, K. Setyo, M. Martianus, and D. Christian, “ScienceDirect ScienceDirect Improving Indonesian emotion detection with openAI o4-mini Improving Indonesian emotion detection with openAI o4-mini text normalization text normalization,” Procedia Comput. Sci., vol. 269, pp. 863–871, 2025, doi: 10.1016/j.procs.2025.09.029.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
