LSTM-Based Deep Learning Approach for Hoax Detection on Indonesian Social Media
DOI:
https://doi.org/10.30865/ijics.v10i2.9899Keywords:
Deep Learning, Hoax Detection, Indonesian Text Classification, LSTM, Social MediaAbstract
The widespread adoption of social media, particularly Facebook, has drastically accelerated information dissemination while simultaneously amplifying the spread of misinformation. Hoax content poses a serious threat to public trust and social cohesion. This study proposes a hoax classification system based on the Long Short-Term Memory (LSTM) architecture, selected for its inherent ability to model sequential dependencies in textual data. The experimental workflow covered text preprocessing (case folding, tokenization, stopword removal, and stemming), word vectorization using the Keras Tokenizer, and end-to-end LSTM model training on the “Indonesian Fact and Hoax Political News” dataset from Kaggle, totaling 4,502 samples with a balanced 80:20 train-test split. Experimental results demonstrate the proposed model achieves 92.44% accuracy, 92.63% precision, 92.22% recall, and a 92.42% F1-score on the test set. These findings confirm that LSTM effectively captures contextual and sequential linguistic patterns in Indonesian-language content, offering a viable and scalable solution for automated hoax detection on social media platforms.
References
[1] P. W. Cahyo and U. S. Aesyi, “Perbandingan LSTM dengan Support Vector Machine dan Multinomial Naïve Bayes pada Klasifikasi Kategori Hoax,” vol. 20, no. 2, pp. 23–29, 2023.
[2] A. Wenang, K. A. Widianto, and M. E. Nugraha, “Implementasi Model Deep Learning IndoBERT dengan Antarmuka Aplikasi Mobile untuk Deteksi Berita Hoaks Berbahasa Indonesia,” vol. 5, no. 2, pp. 99–113, 2025.
[3] P. Ramadani et al., “Klasifikasi Berita Hoaks Menggunakan Algoritma Support Vector Machine,” no. November, 2025.
[4] R. Yunanto, A. P. Purfini, and A. Prabuwisesa, “Survei Literatur : Deteksi Berita Palsu Menggunakan Pendekatan Deep Learning,” vol. xx, pp. 118–130, 2021, doi: 10.34010/jamika.v11i2.493.
[5] S. Herdiyani, L. Auliana, and I. Sukoco, “PERANAN MEDIA SOSIAL DALAM MENGEMBANGKAN SUATU BISNIS :,” vol. 18, no. 2, pp. 103–121, 2022.
[6] H. Kopi, J. Pendek, and D. A. N. Jangka, “Penerapan lstm dalam deep learning untuk prediksi harga kopi jangka pendek dan jangka panjang,” vol. 10, no. 1, pp. 554–564, 2025.
[7] F. Santoso and F. Lazim, “G-Tech : Jurnal Teknologi Terapan,” vol. 8, no. 3, pp. 1749–1758, 2024.
[8] A. Hanafiah, Y. Arta, H. O. Nasution, and Y. D. Lestari, “BULLETIN OF COMPUTER SCIENCE RESEARCH Penerapan Metode Recurrent Neural Network dengan Pendekatan Long Short-Term Memory ( LSTM ) Untuk Prediksi Harga Saham,” vol. 4, no. 1, pp. 27–33, 2023, doi: 10.47065/bulletincsr.v4i1.321.
[9] W. Afandi et al., “Klasifikasi Judul Berita Clickbait menggunakan RNN-,” vol. 7, no. 2, pp. 85–89, 2022.
[10] F. Salim et al., “Jurnal Computer Science and Information Technology ( CoSciTech ) Klasifikasi Berita Palsu Menggunakan Pendekatan Hybrid CNN-LSTM Fake News Classification Using Hybrid CNN-LSTM Approach,” vol. 6, no. 1, pp. 55–59, 2025.
[11] S. Merinda, C. Ciksadan, and M. Fadhli, “Perbandingan Algoritma Support Vector Machine dan Bi-Directional Long Short Term Memory Dalam Mengklasifikasi Berita Hoaks,” vol. 7, no. 1, pp. 367–378, 2025, doi: 10.47065/bits.v7i1.7391.
[12] V. No, J. Hal, M. D. Desriansyah, and I. Utna, “Analisis Efektivitas Algoritma Machine Learning dalam Deteksi Hoaks : Pada Berita Digital Berbahasa Indonesia,” vol. 3, no. 2, pp. 63–69, 2025.
[13] A. Sudrajat and R. R. Wulandari, “Indonesian Language Hoax News Classification Based on Naïve Bayes,” vol. 7, no. 1, pp. 70–79, 2022.
[14] K. A. Mumbunan et al., “Perbandingan Algoritma Naive Bayes Dan Support Vector Machine Dalam Deteksi Berita Hoax Berbahasa Indonesia,” vol. 4, no. 1, pp. 52–64, 2025.
