Penerapan Metode Indobert untuk Deteksi Berita Hoaks pada Media Digital Berbahasa Indonesia
DOI:
https://doi.org/10.30998/94zt3k10Keywords:
natural language processing, fine-tuning, klasifikasi teks, deteksi hoaks, IndoBERTAbstract
This study focuses on the implementation of the IndoBERT method for detecting hoax news in Indonesian digital media and examining the model’s performance and generalization ability. The dataset consists of primary data obtained from a Kaggle dataset and secondary data collected through web scraping from various sources, which are then combined and preprocessed. The model is trained using a fine-tuning approach with variations in parameters such as learning rate, batch size, and epoch to achieve optimal results. The experimental results indicate that the best configuration is achieved at epoch 4, learning rate 5e-5, and batch size 16, producing an accuracy of 0.9868 along with the lowest validation loss. Evaluation using a confusion matrix shows a relatively low error rate for both classes. Testing on new data reveals that the model correctly classifies 26 out of 30 samples, indicating good generalization capability, although some misclassifications still occur in factual news that share similar characteristics with hoaxes.
Downloads
References
Bodhi Wijaya, L., Nuraga Wicaksana, Y., Widhiasari, S. S., & Saptawijaya, A. (2024). Wijaya dkk: Pengembangan Model Deteksi Hoaks Berbahasa Indonesia Menggunakan Kombinasi IndoBERT dan BiLSTM Pengembangan Model Deteksi Hoaks Berbahasa Indonesia Menggunakan Kombinasi IndoBERT dan BiLSTM (Vol. 2).
Cistia Sukmawati, E., Suryaningrum, L., Angelica, D., & Ghaniaviyanto Ramadhan, N. (n.d.). Klasifikasi Berita Palsu Menggunakan Model Bidirectional Encoder Representations From Transformers (BERT).
Fardhina, A., Siregar, R. M., Br Sibarani, M. R. W., Br Ginting, I. C., & Pratama, A. (2025). Sistem Deteksi Berita Hoaks berbasis Algoritma Natural Language Processing (NLP) menggunakan BERT. Jurnal Manajemen Informatika, Sistem Informasi Dan Teknologi Komputer (JUMISTIK), 4(1), 450–461. https://doi.org/10.70247/jumistik.v4i1.156
Hanum, A. R., Zetha, I. A., Fajrina, J. N., Wulandari, R. A., Putri, S. C., Andina, S. P., & Yudistira, N. (2024). Analisis Kinerja Algoritma Klasifikasi Teks Bert Dalam Mendeteksi Berita Hoaks. 11(3), 537–546. https://doi.org/10.25126/jtiik2024118093
Jayadianti, H., Kaswidjanti, W., Utomo, A. T., Saifullah, S., Dwiyanto, F. A., & Drezewski, R. (2022). Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN. ILKOM Jurnal Ilmiah, 14(3), 348–354. https://doi.org/10.33096/ilkom.v14i3.1505.348-354
Jocelynne, C., Tobing, L., Lanang Wijayakusuma, I., Putu, L., & Harini, I. (2025). Detection of Political Hoax News Using Fine-Tuning IndoBERT. In Journal of Applied Informatics and Computing (JAIC) (Vol. 9, Number 2). http://jurnal.polibatam.ac.id/index.php/JAIC
Musthafa, A., Muriyatmoko, D., Kamal Sholihin, S., Studi Teknik Informatika, P., Sains dan Teknologi, F., & Darussalam Gontor, U. (n.d.). Deteksi Berita Salah Pada Pemilihan Umum Presiden 2024 Menggunakan Metode Naïve Bayes Berbasis Website.
Rahutomo, F., Yanuar Risca Pratiwi, I., Mayangsari Ramadhani, D., & Negeri Malang Jalan Soekarno Hatta No, P. (2019). Eksperimen Naïve Bayes Pada Deteksi Berita Hoax Berbahasa Indonesia Naïve Bayes’s Experiment On Hoax News Detection In Indonesian Language.
Rijal, M., Musa, H., Seli, F. Y., Asnawi, N. I., & Firman, A. M. (2025). Fake News Detection in Indonesian Language Using a Deep Learning Approach with Indo-BERT.
Roshinta, T. A., Kumala, E., & Dinata, I. F. (2023). Sistem Deteksi Berita Hoax Berbahasa Indonesia Bidang Kesehatan. Remik, 7(2), 1167–1173. https://doi.org/10.33395/remik.v7i2.12369
Sayarizki, P., & Nurrahmi, H. (2024). Implementation of IndoBERT for Sentiment Analysis of Indonesian Presidential Candidates. Journal on Computing, 9(2), 61–72. https://doi.org/10.34818/indojc.2024.9.2.934
Sholikhah, I. I., Tri, A., Harjanta, J., & Latifah, K. (n.d.). Machine Learning Untuk Deteksi Berita Hoax Menggunakan BERT. 2023. Retrieved https://binus.ac.id/malang/2022/05/crisp-dm-cross-industry-standard-process-for-data-mining/
Tobing, M., & Weya, I. (2022). Analisis Penataan Obyek Wisata Kawah Putih Tinggi Raja Sebagai Sumber Pendapatan Masyarakat Di Kecamatan Silau Kahean Kabupaten Simalungun. Jurnal Ekuilnomi, 4(1). https://doi.org/10.36985/ekuilnomi.v4i1.335.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 I Gede Bagus Surya Wibawa, I Nyoman Eddy Indrayana, Made Pasek Agus Ariawan (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
