Comparison of Online Gambling Promotion Detection Performance Using DistilBERT and DeBERTa Models
DOI:
https://doi.org/10.30871/jaic.v9i6.11293Keywords:
DistilBERT, DeBERTa, Online Gambling, Transformer, Text ClassificationAbstract
Online gambling promotions on social media have become a serious concern in Indonesia, where perpetrators use ambiguous and disguised language to evade detection. This study compares two transformer-based models, DistilBERT and DeBERTa, in detecting such content within Indonesian YouTube comments. Using a balanced dataset of 6,350 comments, both models were fine-tuned with optimized hyperparameters (learning rate 1e-5, batch size 32, 5 epochs) and evaluated through five-fold cross-validation. Results show that DeBERTa achieves superior performance with 99.84% accuracy and perfect recall, while DistilBERT achieves 99.29% accuracy. Error and linguistic analyses indicate that DeBERTa’s disentangled attention and Byte-Pair Encoding provide better understanding of non-standard and ambiguous language. Despite requiring higher computational cost, DeBERTa is ideal for high-accuracy applications, whereas DistilBERT remains suitable for real-time and resource-limited environments.
Downloads
References
[1] RRI Data (2024), Data Statistika Penggunaan Media Sosial Masyarakat Indonesia. https://www.rri.co.id/iptek/721570/ini-data-statistik-penggunaan-media-sosial-masyarakat-indonesia-tahun-2024.
[2] R. Bayu Perdana, I. Budi, A. Budi Santoso, A. Ramadiah, and P. Kresna Putra, “Detecting Online Gambling Promotions on Indonesian Twitter Using Text Mining Algorithm,” 2024. [Online]. Available: www.ijacsa.thesai.org
[3] A. Maulana and A. Yuliana, “Analisis Sentimen Opini Publik Terkait Judi Online Pada Pengguna Aplikasi X Menggunakan Algoritma Naïve Bayes Dan Support Vector Mechine,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 3S1, Oct. 2024, doi: 10.23960/jitet.v12i3S1.5187.
[4] E. Smith, N. Reiter, and J. Peters, “Automatic detection of problem-gambling signs from online texts using large language models,” Nov. 2023, [Online]. Available: http://arxiv.org/abs/2312.00804
[5] F. Fajri et al., “Membandingkan Nilai Akurasi BERT dan DistilBERT pada Dataset Twitter,” vol. 8, no. 2, pp. 71–80, 2022.
[6] V. Sanh, L. Debut, J. Chaumond, and T. Wolf, “DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter,” Oct. 2019, [Online]. Available: http://arxiv.org/abs/1910.01108
[7] J. Carreras Timoneda and S. Vallejo Vera, “BERT, RoBERTa or DeBERTa? Comparing Performance Across Transformer Models in Political Science Text,” J Polit, Jan. 2024, doi: 10.1086/730737.
[8] S. Ruder, M. Peters, S. Swayamdipta, and T. Wolf, “Ruder, S. (2019). Transfer Learning in Natural Language Processing. arXiv preprint arXiv:1901.11504.”
[9] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016.
[10] A. Chopra, A. Prashar, and C. Sain, “Natural Language Processing,” International Journal Of Technology Enhancements And Emerging Engineering Research, vol. 1, no. 4, 2013, [Online]. Available: http://en.wikipedia.org/wiki/
[11] C. Jocelynne, L. Tobing, I. Lanang Wijayakusuma, L. Putu, and I. Harini, “Detection of Political Hoax News Using Fine-Tuning IndoBERT,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[12] Vasmani, A., Shazeer, N., Parman, N., Uszkoreit, J., Jones, L., Gomez, A., & Kaiser, L. (2017) Attention is all you need. URL https://proceedings.neurips.cc/paper_files/paper/ 2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf.”
[13] P. He, X. Liu, J. Gao, and W. Chen, “DeBERTa: Decoding-enhanced BERT with Disentangled Attention,” Jun. 2020, doi: https://doi.org/10.48550/arXiv.2006.03654.
[14] M. B. Nugroho, A. Khanif Zyen, and A. Widiastuti, “Multiclass Sentiment Analysis of Electric Vehicle Incentive Policies Using IndoBERT and DeBERTa Algorithms,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[15] S. Mahendru and T. Pandit, “SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection,” Jun. 2024, doi: 10.1109/BDAI62182.2024.10692765.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Halim Meliana Pratama, IGN Lanang Wijayakusuma, Ratna Sari Widiastuti
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
