Fake News Classification Using Hybrid CNN-LSTM Approach
Abstract
Fake news detection has become a major challenge in the rapidly evolving digital era. This study proposes a hybrid approach combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) to enhance the accuracy of fake news classification. CNN is utilized to extract local features from text, while LSTM captures temporal relationships in sequential data. The dataset used is sourced from Kaggle, consisting of 44,919 fake and real news articles. The classification process includes several stages, such as data preprocessing, tokenization, and transforming text into numerical representations before being processed by the hybrid CNN-LSTM model. Evaluation results indicate that the hybrid CNN-LSTM model achieves an accuracy of 99%, outperforming individual CNN and LSTM models. With high precision and recall rates, this method proves to be effective in classifying fake news, significantly contributing to the development of a more accurate and reliable fake news detection system.
Downloads
References
[2] D. Rianto Rahadi, “PERILAKU PENGGUNA DAN INFORMASI HOAX DI MEDIA SOSIAL.”
[3] ISCAIE 2020 : IEEE 10th Symposium on Computer Applications and Industrial Electronics : Malaysia, 18-19 April 2020. IEEE, 2020.
[4] F. Rahutomo, I. Y. R. Pratiwi, and D. M. Ramadhani, “Eksperimen Naïve Bayes Pada Deteksi Berita Hoax Berbahasa Indonesia,” JURNAL PENELITIAN KOMUNIKASI DAN OPINI PUBLIK, vol. 23, no. 1, Jul. 2019, doi: 10.33299/JPKOP.23.1.1805.
[5] S. Ananth, D. K. Radha, S. , D. Prema, and K. Nirajan, “Fake News Detection using Convolution Neural Network in Deep Learning,” International Journal Of Innovative Research In Computer And Communication Engineering, 2019.
[6] O. A. H. H. Al-Dulaimi and S. Kurnaz, “A Hybrid CNN-LSTM Approach for Precision Deepfake Image Detection Based on Transfer Learning,” Electronics (Switzerland), vol. 13, no. 9, May 2024, doi: 10.3390/electronics13091662.
[7] “fake-and-real-news-dataset.” Accessed: Jan. 08, 2025. [Online]. Available: https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset
[8] S. SATRIA, Sumijan, and Billy Hendrik, “Implementasi Convolutional Neural Netowork Untuk Klasifikasi Citra KTP-El,” Jurnal CoSciTech (Computer Science and Information Technology), vol. 5, no. 1, pp. 169–176, May 2024, doi: 10.37859/coscitech.v5i1.6708.
[9] I. Goodfellow, Y. Bengio, and A. Courville, “Deep Learning.”
[10] A. Agga, A. Abbou, M. Labbadi, Y. El Houm, and I. H. Ou Ali, “CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production,” Electric Power Systems Research, vol. 208, p. 107908, Jul. 2022, doi: 10.1016/J.EPSR.2022.107908.
[11] R. Firdaus, Joni Satria, and B. Baidarus, “Klasifikasi Jenis Kelamin Berdasarkan Gambar Mata Menggunakan Algoritma Convolutional Neural Network (CNN),” Jurnal CoSciTech (Computer Science and Information Technology), vol. 3, no. 3, pp. 267–273, Dec. 2022, doi: 10.37859/coscitech.v3i3.4360.
