Indobertweet-Bilstm For Detecting Cyberbullying In Mixed Indonesian-English Social Media Texts
Indobertweet-Bilstm Untuk Deteksi Cyberbullying Pada Teks Media Sosial Campuran Bahasa Indonesia-Inggris
DOI:
https://doi.org/10.21070/ups.10010Keywords:
BiLSTM, Code-mixed, Cyberbullying detection, Deep learning, Hyperparameter optimization, IndoBERTweet, Sentiment analysisAbstract
Cyberbullying has become a serious issue on Indonesian social media, with approximately 45% of teenagers having experienced it. Platform X exhibits a high rate of cyberbullying, complicated by the code-mixing phenomenon between Indonesian and English. This study develops an optimal cyberbullying detection system through systematic hyperparameter configuration investigation and comprehensive deep learning architecture comparison. We evaluated three optimizers (Adam, AdamW, SGD) with two learning rate schedulers (Linear and Cosine Annealing), and compared six deep learning architectures with one traditional machine learning method. The dataset consisted of 13,677 code-mixed Indonesian tweets (80% training, 10% validation, 10% testing). The IndoBERTweet + BiLSTM model with AdamW optimizer and Cosine Annealing scheduler achieved the best performance: 91.48% accuracy, precision, recall, and F1-score. Adaptive optimizers showed significant impact (19.22% gap vs. SGD), while learning rate schedulers provided consistent improvement of 0.33%. IndoBERTweet improved accuracy by 2.7%-3.8%, outperforming the SVM + TF-IDF baseline (78.18%) by 13.3%.
Downloads
References
A. N. Alfifa, V. Fahira, R. Batubara, K. Sakinah, J. Manik, and R. A. Yoes, “Media Sosial dan Pembentukan Opini Publik (Analisis Studi Kasus Echo Chamber Pada Interaksi Komentar di Akun Instagram @Turnbackhoaxid Dalam Konteks Post-Truth),” J. Penelit. Ilmu-Ilmu Sos., vol. 2, no. 6, pp. 162–169, 2025, [Online]. Available: https://ojs.daarulhuda.or.id/index.php/Socius/article/view/1130
S. Widi, “Pengguna Media Sosial Di Indonesia Sebanyak 167 Juta Pada 2023,” dataindonesia.id. [Online]. Available: https://dataindonesia.id/internet/detail/pengguna-media-sosial-diindonesia-sebanyak-167-juta-pada-2023
F. A. Imani, A. Kusmawati, and H. M. T. Amin, “Pencegahan Kasus Cyberbullying Bagi Remaja Pengguna Sosial Media,” Khidm. Sos. J. Soc. Work Soc. Serv., vol. 2, no. 1, pp. 74–83, 2021, [Online]. Available: https://jurnal.umj.ac.id/index.php/khidmatsosial/article/view/10433
J. M. Beaton, W. J. Doherty, and L. M. Wenger, “Mothers and fathers coparenting together,” in The Routledge Handbook of Family Communication, London: Routledge, 2012, pp. 237–252. [Online]. Available: https://www.taylorfrancis.com/chapters/edit/10.4324/9780203848166-22/mothers-fathers-coparenting-together-john-beaton-william-doherty-lisa-wenger
A. Sukmawati, A. Puput, and B. Kumala, “Dampak Cyberbullying Pada Remaja Di Media Sosial,” Alauddin Sci. J. Nurs., vol. 2020, no. 1, pp. 55–65, 2020, [Online]. Available: http://journal.uin-alauddin.ac.id/index.php/asjn/issue/view/1328
M. S. Jinan, M. R. Handayani, M. A. Ulinuha, and K. Umam, “Muhammad Syifaaul Jinan 1) , Maya Rini Handayani 2) , Masy Ari Ulinuha 3) , Khothibul Umam* 4),” vol. 10, no. 3, pp. 2666–2678, 2025.
Al-Khowarizmi, I. P. Sari, and H. Maulana, “Detecting Cyberbullying on Social Media Using Support Vector Machine: A Case Study on Twitter,” Int. J. Saf. Secur. Eng., vol. 13, no. 4, pp. 709–714, 2023, doi: 10.18280/ijsse.130413.
A. Palagati, S. K. Balan, S. Arun Joe Babulo, L. Raja, K. K. Natarajan, and R. Kalimuthu, “Comparative Analysis of Machine Learning Algorithms and Datasets for Detecting Cyberbullying on Social Media Platforms,” Int. Conf. Comput. Intell. Real. Technol. Proc. ICCIRT 2024, pp. 391–396, 2024, doi: 10.1109/ICCIRT59484.2024.10922033.
N. Novalita, A. Herdiani, I. Lukmana, and D. Puspandari, “Cyberbullying identification on twitter using random forest classifier,” J. Phys. Conf. Ser., vol. 1192, no. 1, 2019, doi: 10.1088/1742-6596/1192/1/012029.
A. U. Rehman, A. K. Malik, B. Raza, and W. Ali, “A Hybrid CNN-LSTM Model for Improving Accuracy of Movie Reviews Sentiment Analysis,” Multimed. Tools Appl., vol. 78, no. 18, pp. 26597–26613, Sep. 2019, doi: 10.1007/s11042-019-07788-7.
Y. Kim, “Convolutional neural networks for sentence classification,” EMNLP 2014 - 2014 Conf. Empir. Methods Nat. Lang. Process. Proc. Conf., pp. 1746–1751, 2014, doi: 10.3115/v1/d14-1181.
N. Abdulloh and A. F. Hidayatullah, “Deteksi Cyberbullying pada Cuitan Media Sosial Twitter,” Automata, vol. Vol 1, no. 1, pp. 1–5, 2021.
M. F. Rizki, K. Auliasari, and R. Primaswara Prasetya, “Analisis Sentiment Cyberbullying Pada Sosial Media Twitter Menggunakan Metode Support Vector Machine,” JATI (Jurnal Mhs. Tek. Inform., vol. 5, no. 2, pp. 548–556, 2021, doi: 10.36040/jati.v5i2.3808.
N. F. Hasan, “Deteksi Cyberbullying pada Facebook Menggunakan Algoritma K-Nearest Neighbor,” J. Smart Syst., vol. 1, no. 1, pp. 35–44, 2021, doi: 10.36728/jss.v1i1.1605.
R. Masbadi Hatullah Nurnaryo, M. Mulaab, I. Oktavia Suzanti, D. Abdul Fatah, A. D. Cahyani, and F. Ayu Mufarroha, “Deteksi Cyberbullying Pada Data Tweet Menggunakan Metode Random Forest Dan Seleksi Fitur Information Gain,” J. Simantec, vol. 11, no. 1, pp. 33–40, 2022, doi: 10.21107/simantec.v11i1.17256.
H. Santoso, R. A. Putri, and S. Sahbandi, “Deteksi Komentar Cyberbullying pada Media Sosial Instagram Menggunakan Algoritma Random Forest,” J. Manaj. Inform., vol. 13, no. 1, pp. 62–72, 2023, doi: 10.34010/jamika.v13i1.9303.
Fauzan Baehaqi and N. Cahyono, “Analisis Sentimen Terhadap Cyberbullying Pada Komentar Di Instagram Menggunakan Algoritma Naïve Bayes,” Indones. J. Comput. Sci., vol. 13, no. 1, pp. 1051–1063, 2024, doi: 10.33022/ijcs.v13i1.3301.
A. Machmud, B. Wibisono, and N. Suryani, “Analisis Sentimen Cyberbullying Pada Komentar X Menggunakan Metode Naïve Bayes,” vol. 5, no. 1, 2025.
R. Triyana, O. Virgantara Putra, and F. R. Pradhana, “Deteksi Cyberbullying Pada Tweet Berbahasa Inggris Dengan Metode Support Vector Machine,” Semin. Nas. Has. Penelit. Pengabdi. Masy. Bid. Ilmu Komput., pp. 98–103, 2022.
P. Widiyantoro and Y. D. Prasetyo, “Deteksi Cyberbullying pada Pemain Sepak Bola di Platform Media Sosial ‘ X ’ Menggunakan Metode Long Short-Term Memory ( LSTM ),” 2025.
A. J. Andika, Y. Kristian, and E. I. Setiawan, “Deteksi Komentar Cyberbullying Pada YouTube Dengan Metode Convolutional Neural Network – Long Short-Term Memory Network (CNN-LSTM),” Teknika, vol. 12, no. 3, pp. 183–188, 2023, doi: 10.34148/teknika.v12i3.677.
M. A. Rosid, D. Siahaan, and A. Saikhu, “Sarcasm Detection in Indonesian-English Code-Mixed Text Using Multihead Attention-Based Convolutional and Bi-Directional GRU,” IEEE Access, no. July, pp. 137063–137079, 2024, doi: 10.1109/ACCESS.2024.3436107.
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” NAACL HLT 2019 - 2019 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol. - Proc. Conf., vol. 1, pp. 4171–4186, 2019.
M. Safitri et al., “DETEKSI CYBERBULLYING TWEET MENGGUNAKAN MACHINE,” pp. 370–374, 2025.
P. H. Zakaria, D. Nurjannah, and H. Nurrahmi, “Misogyny Text Detection on Tiktok Social Media in Indonesian Using the Pre-trained Language Model IndoBERTweet,” J. Media Inform. Budidarma, vol. 7, no. 3, p. 1297, 2023, doi: 10.30865/mib.v7i3.6438.
J. Forry Kusuma and A. Chowanda, “INTERNATIONAL JOURNAL ON INFORMATICS VISUALIZATION journal homepage : www.joiv.org/index.php/joiv INTERNATIONAL JOURNAL ON INFORMATICS VISUALIZATION Indonesian Hate Speech Detection Using IndoBERTweet and BiLSTM on Twitter,” vol. 7, no. September, pp. 773–780, 2023, [Online]. Available: www.joiv.org/index.php/joiv
S. Nauli, S. S. Berutu, H. Budiati, and F. Maedjaja, “Klasifikasi Kalimat Perundungan Pada Twitter Menggunakan Algoritma Support Vector Machine,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 10, no. 1, pp. 107–122, 2025, doi: 10.29100/jipi.v10i1.5749.
Downloads
Additional Files
Posted
License
Copyright (c) 2026 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
