Indonesian Hoax News Detection Using One-Dimensional Convolutional Neural Network
Abstract
The rapid advancement of information technology has enabled global information dissemination and led to a surge in hoax news, particularly in Indonesia. Hoax news poses a significant risk of spreading disinformation, potentially influencing public opinion, social stability, and security. Therefore, an effective technology-based solution is required to detect and identify hoaxes. This study aims to develop and optimize a one-dimensional convolutional neural network (1D-CNN) model to detect hoax news with high accuracy. The dataset comprised 12,151 articles, including 5,276 valid news items and 6,875 hoax news items, collected from reliable sources and anti-hoax platforms. The text preprocessing stages included data cleaning, case folding, punctuation removal, number removal, and stopword removal. The textual data were processed through tokenization and padding stages for model training preparation. The proposed 1D-CNN architecture integrated embedding, Conv1D, batch normalization, globalmaxpooling1d, dense, and dropout layers to enhance generalization capabilities and reduce the risk of overfitting. The model was trained using the Adam optimizer and its performance was evaluated using 10-fold cross-validation. Experimental results showed that the model achieved an average accuracy, precision, recall, and F1 score of 97.74%, 97.75%, 97.74%, and 97.73%, respectively. The developed model outperformed previous methods, namely the convolutional neural network–bidirectional long short-term memory (CNN-BiLSTM), gated recurrent unit (GRU), and conventional methods such as naïve Bayes or support vector machine (SVM), in terms of accuracy and training efficiency. This study demonstrates that the model has a reliable capability in identifying hoax news, both in terms of detection accuracy and performance consistency.
References
B.P. Nayoga, R. Adipradana, R. Suryadi, and D. Suhartono, “Hoax analyzer for Indonesian news using deep learning models,” Procedia Comput. Sci., vol. 179, pp. 704–712, Feb. 2021, doi: 10.1016/j.procs.2021.01.059.
Mukhlizar and F. Yuliani, “Hoax dan tanggung jawab sosial pengguna sosial media,” Kaganga, J. Pendidik. Sej. Ris. Sos. Hum., vol. 6, no. 2, pp. 461–466, Jul.-Dec. 2023, doi: 10.31539/kaganga.v6i2.7695.
T.C. Praha, Widodo, and Murien Nugraheni, “Indonesian fake news classification using transfer learning in CNN and LSTM,” JOIV, Int. J. Inform. Visualization, vol. 8, no. 3, pp. 1213–1220, Sep. 2024, doi: 10.62527/joiv.8.2.2126.
D. Amelia et al., “Variabel yang memengaruhi kemampuan literasi membaca siswa Indonesia: Analisis berdasarkan pendekatan MARS,” J. Pendidik. Kebud., vol. 9, no. 2, pp. 205–217, Dec. 2024, doi: 10.24832/jpnk.v9i2.4966.
J.C.S. Reis et al., “Supervised learning for fake news detection,” IEEE Intell. Syst., vol. 34, no. 2, pp. 76–81, Mar./Apr. 2019, doi: 10.1109/MIS.2019.2899143.
A.D. Safira and E.B. Setiawan, “Hoax detection in social media using bidirectional long short-term memory (Bi-LSTM) and 1 dimensional-convolutional neural network (1D-CNN) methods,” in 2023 11th Int. Conf. Inf. Commun. Technol. (ICoICT), 2023, pp. 355–360, doi: 10.1109/ICoICT58202.2023.10262528.
M.F. Mridha et al., “A comprehensive review on fake news detection with deep learning,” IEEE Access, vol. 9, pp. 156151–156170, Nov. 2021, doi: 10.1109/ACCESS.2021.3129329.
M.G. Ayu, “Peneliti manfaatkan AI untuk deteksi berita palsu COVID-19.” Cloud Computing Indonesia. Access date: 20-Nov-2024. [Online]. Available: https://www.cloudcomputing.id/berita/peneliti-manfaatkan-ai-dalam-mendeteksi-berita-palsu
S. Kiranyaz et al., “1D convolutional neural networks and applications: A survey,” Mech. Syst. Signal Process., vol. 151, pp. 1–21, Apr. 2021, doi: 10.1016/j.ymssp.2020.107398.
R. Oshikawa, J. Qian, and W. Y. Wang, “A survey on natural language processing for fake news detection,” in Proc. 12th Lang. Resour. Eval. Conf., 2020, pp. 6086–6093.
M. Benedict and E.B. Setiawan, “Hoax detection on social media with convolutional neural network (CNN) and support vector machine (SVM),” in 2023 11th Int. Conf. Inf. Commun. Technol. (ICoICT), 2023, pp. 361–366, doi: 10.1109/ICoICT58202.2023.10262433.
X. Zhang, J. Zhao, and Y. LeCun, “Character-level convolutional networks for text classification,” in NIPS'15, Proc. 29th Int. Conf. Neural Inf. Process. Syst., 2015, pp. 649–657.
O.C.R. Rachmawati and Z.M.E. Darmawan, “The comparison of deep learning models for Indonesian political hoax news detection,” CommIT (Commun. Inf. Technol.) J., vol. 18, no. 2, pp. 123–135, Oct. 2024, doi: 10.21512/commit.v18i2.10929.
K.S. Nugroho, “Dasar text preprocessing dengan Python.” Medium. Access date: 20-Oct-2024. [Online]. Available: https://ksnugroho.medium.com/dasar-text-preprocessing-dengan-python-a4fa52608ffe
L. Hu, S. Wei, Z. Zhao, and B. Wu, “Deep learning for fake news detection: A comprehensive survey,” AI Open, vol. 3, pp. 133–155, Oct. 2022, doi: 10.1016/j.aiopen.2022.09.001.
J. Brownlee, “A gentle introduction to k-fold cross-validation.” Access date: 30-Oct-2024. [Online]. Available: https://machinelearningmastery.com/k-fold-cross-validation/
S. Narkhede, “Understanding confusion matrix.” Towards Datascience. Access date: 20-Oct-2024. [Online]. Available: https://towardsdatascience.com/understanding-confusion-matrix-a9ad42dcfd62
S.F.N. Azizah, H.D. Cahyono, S.W. Sihwi, and W. Widiarto, “Performance analysis of transformer based models (BERT, ALBERT and RoBERTa) in fake news detection,” in 2023 6th Int. Conf. Inf. Commun. Technol. (ICOIACT), 2023, pp. 425–430, doi: 10.1109/ICOIACT59844.2023.10455849.
M.A. Rosid et al., “Improving text preprocessing for student complaint document classification using Sastrawi,” in Int. Conf. Eng. Technol. Appl. Sci. (ICETsAS), 2020, pp. 1–6, doi: 10.1088/1757-899X/874/1/012017.
M.G. Pradana, “Penggunaan fitur wordcloud dan document term matrix dalam text mining,” J. Ilm. Inform., vol. 8, no. 1, pp. 38-43, Mar. 2020, doi: 10.33884/jif.v8i01.1838.
R. Egger, “Text representations and word embeddings,” in Applied Data Science in Tourism. Cham, Switzerland: Springer, 2022, pp. 335–361.
C. Garbin, X. Zhu, and O. Marques, “Dropout vs. batch normalization: An empirical study of their impact to deep learning,” Multimed. Tools Appl., vol. 79, no. 19–20, pp. 12777–12815, May 2020, doi: 10.1007/s11042-019-08453-9.
H. Kim and Y.S. Jeong, “Sentiment classification using convolutional neural networks,” Appl. Sci., vol. 9, no. 11, pp. 1–14, Jun. 2019, doi: 10.3390/app9112347.
D.M Merkulov and I.V. Oseledets, “Empirical study of extreme overfitting points of neural networks,” vol. 64, no. 12, pp. 1527-1534, Dec. 2019, doi: 10.1134/s106422691912011.
© Jurnal Nasional Teknik Elektro dan Teknologi Informasi, under the terms of the Creative Commons Attribution-ShareAlike 4.0 International License.
1.png)
