PERBANDINGAN MODEL TRANSFORMER, DEEP LEARNING, DAN MACHINE LEARNING UNTUK DETEKSI BERITA PALSU: STUDI KASUS PADA TEKS BERBAHASA INDONESIA
DOI:
https://doi.org/10.36595/misi.v8i2.1591Keywords:
Berita Palsu, RoBERTa, BERT, IndoBERT, SVM, LSTM, CNN, NLP, TransformerAbstract
Deteksi berita palsu dalam bahasa Indonesia masih menjadi tantangan dalam pemrosesan bahasa alami (NLP). Penelitian ini membandingkan enam metode: RoBERTa, BERT, IndoBERT, SVM, LSTM, dan CNN dalam mengidentifikasi berita palsu. Dataset yang digunakan telah melalui proses pembersihan dan tokenisasi sebelum diterapkan pada masing-masing model. Penelitian ini memberikan analisis komprehensif terhadap keunggulan model Transformer dibandingkan dengan metode klasik seperti SVM, CNN, dan LSTM. Selain itu, penelitian ini juga menegaskan bahwa model yang dilatih khusus untuk bahasa Indonesia, seperti IndoBERT, memiliki performa lebih baik dibandingkan BERT standar. Hasil evaluasi menunjukkan bahwa model berbasis Transformer memiliki performa terbaik, dengan RoBERTa sebagai model paling akurat. Temuan ini dapat menjadi referensi bagi pengembangan sistem deteksi berita palsu yang lebih akurat dan efisien dalam bahasa Indonesia. Akurasi yang diperoleh dari masing-masing model adalah sebagai berikut: RoBERTa (99,5%), IndoBERT (98,6%), BERT (98,2%), SVM (95,9%), CNN (93,9%), dan LSTM (92,3%).
References
M. Guderlei and M. Aßenmacher, “Evaluating Unsupervised Representation Learning for Detecting Stances of Fake News,” Proceedings ofthe 28th International Conference on Computational Linguistics, pp. 6339–6349, 2020, [Online]. Available: https://github.com/magud/fake-news-detection
P. Bahad, P. Saxena, and R. Kamal, “Fake News Detection using Bi-directional LSTM-Recurrent Neural Network,” in Procedia Computer Science, Elsevier B.V., 2019, pp. 74–82. doi: 10.1016/j.procs.2020.01.072.
R. Jehad and S. Yousif, “Classification of fake news using multi-layer percepti on,” in AIP Conference Proceedings, American Institute of Physics Inc., Mar. 2021. doi: 10.1063/5.0042264.
P. Dedeepya, M. Yarrarapu, P. P. Kumar, S. K. Kaushik, P. N. Raghavendra, and P. Chandu, “Fake News Detection on Social Media Through a Hybrid SVM-KNN Approach Leveraging Social Capital Variables,” in 2024 3rd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 2024, pp. 1168–1175. doi: 10.1109/ICAAIC60222.2024.10575681.
Zhang Tong et al., “BDANN: BERT-Based Domain Adaptation Neural Network for Multi-Modal Fake News Detection,” 2020 International Joint Conference on Neural Networks (IJCNN), 2020.
A. Pritzkau, “Multi-class fake news detection of news articles and domain identification with RoBERTa-a baseline model,” CEUR Workshop Proc, Sep. 2021, [Online]. Available: https://www.fkie.fraunhofer.de/
N. Lin, S. Fu, and S. Jiang, “Fake News Detection in the Urdu Language using CharCNN-RoBERTa,” CEUR Workshop Proc, vol. 2826, pp. 447–451, 2020, [Online]. Available: https://huggingface.co/urduhack/urdu-roberta
E. Raja, B. Soni, and S. K. Borgohain, “Fake News Detection in Malayalam using Optimized XLM-RoBERTa Model,” in DravidianLangTech 2023 - 3rd Workshop on Speech and Language Technologies for Dravidian Languages, associated with 14th International Conference on Recent Advances in Natural Language Processing, RANLP 2023 - Proceedings, Incoma Ltd, 2023, pp. 186–191. doi: 10.26615/978-954-452-085-4_026.
S. M. Isa, G. Nico, and M. Permana, “IndoBERT for Indonesian Fake News Detection,” ICIC Express Letters, vol. 16, no. 3, pp. 289–297, Mar. 2022, doi: 10.24507/icicel.16.03.289.
L. B. Angizeh and M. R. Keyvanpour, “Detecting Fake News using Advanced Language Models: BERT and RoBERTa,” in 2024 10th International Conference on Web Research (ICWR), 2024, pp. 46–52. doi: 10.1109/ICWR61162.2024.10533352.
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 International Conference on Information and Communications Technology (ICOIACT), 2023, pp. 425–430. doi: 10.1109/ICOIACT59844.2023.10455849.
V. Kolev, G. Weiss, and G. Spanakis, “FOREAL: RoBERTa Model for Fake News Detection based on Emotions,” in International Conference on Agents and Artificial Intelligence, Science and Technology Publications, Lda, 2022, pp. 429–440. doi: 10.5220/0010873900003116.
M. Umer, Z. Imtiaz, S. Ullah, A. Mehmood, G. S. Choi, and B. W. On, “Fake news stance detection using deep learning architecture (CNN-LSTM),” IEEE Access, vol. 8, pp. 156695–156706, 2020, doi: 10.1109/ACCESS.2020.3019735.
R. Jehad and S. A.Yousif, “Fake News Classification Using Random Forest and Decision Tree (J48),” Al-Nahrain Journal of Science, vol. 23, no. 4, pp. 49–55, Dec. 2020, doi: 10.22401/ANJS.23.4.09.
H. T. Phan, N. T. Nguyen, and D. Hwang, “Fake news detection: A survey of graph neural network methods,” May 01, 2023, Elsevier Ltd. doi: 10.1016/j.asoc.2023.110235.
J. Alghamdi, Y. Lin, and S. Luo, “A Comparative Study of Machine learning and Deep learning Techniques for Fake News Detection,” Information (Switzerland), vol. 13, no. 12, Dec. 2022, doi: 10.3390/info13120576.
D. G. Dev and V. Bhatnagar, “Hybrid RFSVM: Hybridization of SVM and Random Forest Models for Detection of Fake News,” Algorithms, vol. 17, no. 10, Oct. 2024, doi: 10.3390/a17100459.
P. Jain, S. Sharma, Monica, and P. K. Aggarwal, “Classifying Fake News Detection Using SVM, Naive Bayes and LSTM,” in 2022 12th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 2022, pp. 460–464. doi: 10.1109/Confluence52989.2022.9734129.
R. Mohawesh, H. Bany Salameh, Y. Jararweh, M. Alkhalaileh, and S. Maqsood, “Fake review detection using Transformer-based enhanced LSTM and RoBERTa,” International Journal of Cognitive Computing in Engineering, vol. 5, pp. 250–258, Jan. 2024, doi: 10.1016/j.ijcce.2024.06.001.
S. Ghazi Arkaan, A. Rialdy Atmadja, and M. D. Firdaus, “Fake News Detection in the 2024 Indonesian General Election Using Bidirectional Long Short-Term Memory (BI-LSTM) Algorithm,” Jurnal Ilmiah Ilmu Komputer dan Matematika, vol. 21, no. 2, pp. 693–7554, 2024, doi: 10.33751/komputasi.v21i2.5260.
M. Rifky Maulana et al., “PENERAPAN METODE LSTM DALAM PEMBUATAN SISTEM PENDETEKSI BERITA PALSU BERBAHASA INDONESIA,” 2023. [Online]. Available: https://drive.google.com/drive/folders/1eYKx7agpzgvXGCpyE1E57HXDhonk
N. Agustina, A. Adrian, and M. Hermawati, “Implementasi Algoritma Naïve Bayes Classifier untuk Mendeteksi Berita Palsu pada Sosial Media,” Faktor Exacta, vol. 14, no. 4, p. 206, Jan. 2022, doi: 10.30998/faktorexacta.v14i4.11259.
A. Ripa’i, F. Santoso, and F. Lazim, “Deteksi Berita Hoax dengan Perbandingan Website Menggunakan Pendekatan Deep learning Algoritma BERT,” G-Tech: Jurnal Teknologi Terapan, vol. 8, no. 3, pp. 1749–1758, Jul. 2024, doi: 10.33379/gtech.v8i3.4541.
A. A. Kurniawan, M. Mustikasari, and P. Korespondensi, “EVALUASI KINERJA MLLIB APACHE SPARK PADA KLASIFIKASI BERITA PALSU DALAM BAHASA INDONESIA,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 9, no. 3, Jun. 2022, doi: 10.25126/jtiik.202293538.
R. N. Rahayu and & Sensusiyati, “ANALISIS BERITA HOAX COVID-19 DI MEDIA SOSIAL DI INDONESIA,” INTELEKTIVA?: JURNALEKONOMI, SOSIAL & HUMANIORA, vol. 01, Apr. 2020, [Online]. Available: https://www.suara.com/news,
C. F. Navarro and C. A. Perez, “Color-texture pattern classification using global-local feature extraction, an SVM classifier, with bagging ensemble post-processing,” Applied Sciences (Switzerland), vol. 9, no. 15, Aug. 2019, doi: 10.3390/app9153130.
M. Szczepa?ski, M. Pawlicki, R. Kozik, and M. Chora?, “New explainability method for BERT-based model in fake news detection,” Sci Rep, vol. 11, no. 1, Dec. 2021, doi: 10.1038/s41598-021-03100-6.
Downloads
Published
How to Cite
Issue
Section
License
Semua tulisan pada jurnal ini menjadi tanggungjawab penuh penulis.
