Hybrid Cnn-Lstm For Indonesian Cyberbullying Text Classification On Social Media X
Hybrid Cnn-Lstm Untuk Klasifikasi Teks Cyberbullying Bahasa Indonesia Pada Media Sosial X
DOI:
https://doi.org/10.21070/ups.10048Keywords:
cyber bullying, CNN-LSTM, Deep Learning, Social Media X, Indonesian LanguageAbstract
Cyberbullying on social media platform X has become a critical digital threat, requiring automatic detection mechanisms. This study proposes a hybrid deep learning architecture combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to classify Indonesian cyberbullying comments. Using a dataset of 13,677 comments, the study evaluates model performance through systematic scenarios, including regularization and FastText embeddings. Results demonstrate that Early Stopping is critical, preventing a 32% accuracy degradation. The proposed CNN-LSTM model achieves 88.38% accuracy and 0.9559 AUC with FastText integration. Notably, this model attains over 97% of IndoBERTweet's performance with 22 times lower computational complexity (4.97 million vs. 110.88 million parameters) and outperforms SVM by over 10 percentage points. The study concludes that the CNN-LSTM architecture offers a robust, efficient solution for cyberbullying detection, particularly suitable for resource-constrained environments.
Downloads
References
Ahmad, S. R., Insani, N., & Salim, M. (2024). Analysis of Cyberbullying on Social Media Using A Comparison of Naïve Bayes, Random Forest, and SVM Algorithms. Jurnal Teknologi Informasi Dan Pendidikan, 17(1), 75–86. https://doi.org/10.24036/jtip.v17i1.807
Akar, F. (2024). Performance Analysis of NLP-Based Machine Learning Algorithms in Cyberbullying Detection. Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 17(2), 445–459. https://doi.org/10.18185/erzifbed.1474112
Akter, F., Rabbi, F., & Chowdhury, R. R. (2025). Cyberbullying Detection on Social Media Platforms Utilizing Different Machine Learning Approaches. 186(61), 40–50.
Alqahtani, A. F., & Ilyas, M. (2024). An Ensemble-Based Multi-Classification Machine Learning Classifiers Approach to Detect Multiple Classes of Cyberbullying. Machine Learning and Knowledge Extraction, 6(1), 156–170. https://doi.org/10.3390/make6010009
Andika, A. J., Kristian, Y., & Setiawan, E. I. (2023). Deteksi Komentar Cyberbullying Pada YouTube Dengan Metode Convolutional Neural Network – Long Short-Term Memory Network (CNN-LSTM). Teknika, 12(3), 183–188. https://doi.org/10.34148/teknika.v12i3.677
Asqolani, I. A., & Setiawan, E. B. (2023). A Hybrid Deep Learning Approach Leveraging Word2Vec Feature Expansion for Cyberbullying Detection in Indonesian Twitter. Ingenierie Des Systemes d’Information, 28(4), 887–895. https://doi.org/10.18280/isi.280410
Cahyo, D. D. N., Handayani, R., Lestari, V. B., & Febriani, S. (2025). JITE ( Journal of Informatics and Telecommunication Engineering ) Sentiment Analysis of Public Opinion on Online Gambling Through. 9(July), 99–115.
El Koshiry, A. M., Eliwa, E. H. I., El-Hafeez, T. A., & Khairy, M. (2024). Detecting cyberbullying using deep learning techniques: a pre-trained glove and focal loss technique. PeerJ Computer Science, 10, 1–33. https://doi.org/10.7717/peerj-cs.1961
Faritha Banu, J., Rajeshwari, S. B., Kallimani, J. S., Vasanthi, S., Buttar, A. M., Sangeetha, M., & Bhargava, S. (2022). Modeling of Hyperparameter Tuned Hybrid CNN and LSTM for Prediction Model. Intelligent Automation and Soft Computing, 33(3), 1393–1405. https://doi.org/10.32604/iasc.2022.024176
Hafiza, A. A., & Setiawan, E. B. (2025). Enhancing Cyberbullying Detection on Platform “X” Using IndoBERT and Hybrid CNN-LSTM Model. Jurnal Teknik Informatika (Jutif), 6(2), 655–672. https://doi.org/10.52436/1.jutif.2025.6.2.4321
Harish, D., Manimaran, M., Jayashakthi, V. P., & Alamelu, M. (2023). Automatic Detection of Cyberbullying on Social Media Using Machine Learning. 2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2023, 13(3), 185–189. https://doi.org/10.1109/ICAECA56562.2023.10201149
Hasan, M. T., Hossain, M. A. E., Mukta, M. S. H., Akter, A., Ahmed, M., & Islam, S. (2023). A Review on Deep-Learning-Based Cyberbullying Detection. Future Internet, 15(5), 1–47. https://doi.org/10.3390/fi15050179
Iryani, L., Junaidi, J., Paisal, P., Purba, M., Umilizah, N., Bakhtiar, B., & Ani, N. (2025). Model of Cyberbullying Detection on Social Media Using Multi-Label Deep Learning: a Comparative Study. JITK (Jurnal Ilmu Pengetahuan Dan Teknologi Komputer), 10(4), 742–748. https://doi.org/10.33480/jitk.v10i4.6004
Masbadi Hatullah Nurnaryo, R., Mulaab, M., Oktavia Suzanti, I., Abdul Fatah, D., Cahyani, A. D., & Ayu Mufarroha, F. (2022). Deteksi Cyberbullying Pada Data Tweet Menggunakan Metode Random Forest Dan Seleksi Fitur Information Gain. Jurnal Simantec, 11(1), 33–40. https://doi.org/10.21107/simantec.v11i1.17256
Maulana, M. D., & Aditya, C. S. K. (2025). Perbandingan IndoBERT dan Bi-LSTM Dalam Mendeteksi Pelanggaran Undang-Undang ITE. Science And Information Technology (SINTECH), 8(1), 52–59. https://doi.org/10.31598
Mitra, S., Tasnim, T., Islam, M. A. R., Khan, N. I., & Majib, M. S. (2021). A Framework to Detect and Prevent Cyberbullying from Social Media by Exploring Machine Learning Algorithms. 6th International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering, IC4ME2 2021, February 2023. https://doi.org/10.1109/IC4ME253898.2021.9768450
Nasution, M. A. S., & Setiawan, E. B. (2023). Enhancing Cyberbullying Detection on Indonesian Twitter: Leveraging FastText for Feature Expansion and Hybrid Approach Applying CNN and BiLSTM. Revue d’Intelligence Artificielle, 37(4), 929–936. https://doi.org/10.18280/ria.370413
Prama, T. T., Amrin, J. F., Anwar, Md. M., & Sarker, I. H. (2025). AI Enabled User-Specific Cyberbullying Severity Detection with Explainability. 1–25. http://arxiv.org/abs/2503.10650
Purkayastha, B. S., Rahman, M., & Talukdar, T. I. (2025). Advancing Cyberbullying Detection : A Hybrid Machine Learning and Deep Learning Framework for Social Media Analysis. 2(Iceis), 348–355. https://doi.org/10.5220/0013436200003929
Ramadhan, V., Pambudi, A., Informatika, T., & Sukabumi, U. M. (2024). IMPLEMENTASI ALGORITMA CONVOLUTIONAL NEURAL NETWORK UNTUK MENGIDENTIFIKASI BERITA HOAKS BERBAHASA INDONESIA. 8(5), 10945–10952.
Rosid, M. A., Siahaan, D., & Saikhu, A. (2024). Sarcasm Detection in Indonesian-English Code-Mixed Text Using Multihead Attention-Based Convolutional and Bi-Directional GRU. IEEE Access, June, 137063–137079. https://doi.org/10.1109/ACCESS.2024.3436107
Santoso, H., Putri, R. A., & Sahbandi, S. (2023). Deteksi Komentar Cyberbullying pada Media Sosial Instagram Menggunakan Algoritma Random Forest. Jurnal Manajemen Informatika (JAMIKA), 13(1), 62–72. https://doi.org/10.34010/jamika.v13i1.9303
Shubham Singh. (2025). Twitter Statistics 2025: How Many People Use X [New Data]. https://www.demandsage.com/twitter-statistics/
Smote, C. D. I. (2025). Analisis komparatif klasifikasi sentimen pengguna aplikasi investasi menggunakan algoritma hybrid cnn-lstm, cnn-gru dengan implementasi smote. 6, 112–118.
Tapaskar, V., & J, M. C. T. (2024). INTERNATIONAL JOURNAL OF A Multi-Algorithm Approach for Cyberbullying Detection. 7(10). https://doi.org/10.15680/IJMRSET.2024.0710027
Downloads
Additional Files
Posted
License
Copyright (c) 2026 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
