Pengembangan Aplikasi Web Klasifikasi Berita Hoaks Menggunakan Model Long Term-Short Memory (LTSM)
Keywords:
Information Technology, Social Impact, Economic Impact, Society, Digital Divide, MultidisciplinaryAbstract
Fake news has increasingly spread across digital platforms along with the rapid advancement of information and communication technologies. Fake news has a significant impact on public opinion, social stability, and decision-making processes. In this study, a deep learning approach using the Long Short-Term Memory (LSTM) model is employed to develop a web-based fake news classification system. The dataset consists of thousands of news articles collected from various sources, including TurnBackHoax, Kompas, Detik, and Antaranews. The research process involves data collection, text preprocessing, tokenization, LSTM model construction, training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. The proposed model achieves an accuracy of 94.2% on the test dataset, and the classification report and confusion matrix indicate a balanced performance between the fake and legitimate news classes. The developed system is implemented as a web-based application using PHP version 8.2.12, Laravel 9, and PostgreSQL version 10.23, enabling users to perform real-time news classification. The results demonstrate that the LSTM model is effective for analyzing news text and can be utilized to reduce the dissemination of misinformation. This research is expected to provide both academic and practical contributions to the development of technologies for fake news detection.
Abstrak
Berita hoaks semakin menyebar di platform digital seiring dengan kemajuan teknologi informasi dan komunikasi. Berita hoaks memiliki dampak yang signifikan terhadap opini publik, stabilitas sosial, dan pengambilan keputusan. Metode pembelajaran mendalam (deep learning) model Long Short-Term Memory (LSTM) digunakan dalam penelitian ini untuk membangun sistem klasifikasi berita hoaks berbasis web. Data yang digunakan terdiri dari ribuan artikel berita dari berbagai sumber, seperti TurnBackHoax, Kompas, Detik, dan Antaranews. Pengumpulan data, preprocessing teks, tokenisasi, pembentukan model LSTM, pelatihan, dan evaluasi performa menggunakan metrik akurasi, presisi, recall, dan skor F1 adalah semua bagian dari proses penelitian. Model yang dibuat berhasil mencapai akurasi 94,2% pada data uji, dan laporan klasifikasi dan confusion matrix menunjukkan bahwa kelas berita valid dan hoaks seimbang. Sistem ini berfungsi sebagai aplikasi berbasis web dengan PHP 8.2.12, Laravel 9 dan PostgreSQL 10.23. Ini memungkinkan pengguna melakukan klasifikasi berita secara real-time. Penelitian ini menunjukkan bahwa LSTM adalah alat yang baik untuk menganalisis teks berita dan dapat digunakan untuk mengurangi penyebaran informasi yang tidak benar. Penelitian ini diharapkan dapat memberikan kontribusi akademik dan praktis dalam proses pengembangan teknologi yang mendeteksi hoaks.
References
(Almarashy et al., 2023; Dal Forno et al., 2025; Hoy & Koulouri, 2025; Ikasari et al., 2025, 2025; KUSUMA et al., 2025; Lawal & Abdulrauf, 2025; Pekandi et al., 2025; Prastyo & Faisal, 2024; Raja et al., 2024, 2024, 2024; Singh et al., 2025, 2025; Sovia et al., 2025; Tanaja et al., 2025; Widhi et al., 2023)
Almarashy, A. H. J., Feizi-Derakhshi, M. R., & Salehpour, P. (2023). Enhancing Fake News Detection by Multi-Feature Classification. IEEE Access, 11, 139601–139613. https://doi.org/10.1109/ACCESS.2023.3339621
Dal Forno, A. J., Richetti, G. P., & Knaesel, V. H. (2025). Fake news detection algorithms – A systematic literature review. Data and Knowledge Engineering, 158. https://doi.org/10.1016/j.datak.2025.102441
Hoy, N., & Koulouri, T. (2025). An exploration of features to improve the generalisability of fake news detection models. Expert Systems with Applications, 275. https://doi.org/10.1016/j.eswa.2025.126949
Ikasari, I. H., Rosyani, P., & Amalia, R. (2025). Klasifikasi Jenis Buah Menggunakan Metode CNN. RIGGS: Journal of Artificial Intelligence and Digital Business, 4(2), 5451–5458. https://doi.org/10.31004/riggs.v4i2.1271
KUSUMA, S. D. Y., AL ISLAMI, H., & ROSYANI, P. (2025). Penerapan Naive Bayes Untuk Klasifikasi Penyakit Endokrin Pada Pasien Lansia. KERNEL: Jurnal Riset Inovasi Bidang Informatika Dan Pendidikan Informatika, 5(2), 72–82. https://doi.org/10.31284/j.kernel.2024.v5i2.7312
Lawal, M. M., & Abdulrauf, A. (2025). Fake News Detection Using Bi-LSTM Architecture: A Deep Learning Approach on the ISOT Dataset. Journal of Computing Theories and Applications, 3(2), 104–114. https://doi.org/10.62411/jcta.14235
Pekandi, L. A., Widjaja, R. G., Ananta, A., Harefa, J., & Jingga, K. (2025). Evaluating IndoBERT for Indonesian Hoax News Detection: A Comparative Study with Ensemble and CNN-LSTM Models. Procedia Computer Science, 269, 1625–1633. https://doi.org/10.1016/j.procs.2025.09.105
Prastyo, E. H. A., & Faisal, M. (2024). Meningkatkan Akurasi Deteksi Berita Palsu dengan Pendekatan Berbasis Lexicon dan LSTM melalui Text Preprocessing dan Model Training. Jurnal Media Informatika Budidarma, 8(3), 1746. https://doi.org/10.30865/mib.v8i3.7847
Raja, E., Soni, B., & Borgohain, S. K. (2024). Fake news detection in Dravidian languages using multiscale residual CNN_BiLSTM hybrid model. Expert Systems with Applications, 250. https://doi.org/10.1016/j.eswa.2024.123967
Singh, S. P., Kumar, N., Kumar, G., & Ahamed, A. S. (2025). A hybrid deep learning and differential evolution approach for accurate fake news detection. Systems and Soft Computing, 7. https://doi.org/10.1016/j.sasc.2025.200365
Sovia, R., Valkyrie, D. A., Zain, R. H., & Firdaus. (2025). Language Processing for Detecting Fake News on Twitter Using a Long Short-Term Memory Architecture. Jurnal RESTI, 9(4), 935–943. https://doi.org/10.29207/resti.v9i4.6570
Tanaja, R. N., Johnny, Rafif, M. A., & Santoso Gunawan, A. A. (2025). Fake News Detection using Machine Learning: Integrating FakeBERT Classification, Style Analysis, and Credibility Verification. Procedia Computer Science, 269, 1067–1076. https://doi.org/10.1016/j.procs.2025.09.048
Widhi, E. P., Fudholi, D. H., & Hidayat, S. (2023). Implementation Of Deep Learning For Fake News Classification In Bahasa Indonesia. Journal Research of Social Science, Economics, and Management, 3(02), 370–381. https://doi.org/10.59141/jrssem.v3i02.546
Downloads
-
PDF FULL TEXT
Abstract Dilihat : 101 Kali ,
Download: 23 Kali
Published
Issue
Section
License
Copyright (c) 2025 Afriaty Rohmah, Alya Salsabila Az Zahra, Muhammad Sholahuddin A, Tri Prasetyo

This work is licensed under a Creative Commons Attribution 4.0 International License.