Implementasi Model BERT untuk Klasifikasi Konten Hoaks pada Berita Politik
Abstract
The rapid growth of digital media accelerates the spread of information, including political hoaxes that can influence public opinion and disrupt social stability. Distinguishing factual news from hoaxes is challenging due to linguistic complexity and the high volume of textual data that cannot be handled manually. To address this issue, the present study employs an automated approach based on the BERT (Bidirectional Encoder Representations from Transformers) model, which is designed to capture linguistic context in a more comprehensive manner. The dataset consists of 3,807 Indonesian political news articles verified as factual or hoaxes. The results show that BERT achieves 98% accuracy, performing strongly on factual news and reasonably well on hoax detection. These findings confirm that BERT is effective for political hoax classification and serves as a relevant foundation for developing future NLP-based misinformation detection systems.
Keywords: BERT; Fake news; Political news; Text classification
Abstrak
Perkembangan media digital mempercepat penyebaran informasi, termasuk berita hoaks yang berpotensi memengaruhi opini publik dan stabilitas sosial. Tantangan utama dalam memilah fakta dan hoaks terletak pada kompleksitas bahasa serta tingginya volume teks yang sulit ditangani secara manual. Untuk mengatasi permasalahan tersebut, penelitian ini mengadopsi metode otomatis berbasis model BERT (Bidirectional Encoder Representations from Transformers) yang dirancang untuk memahami konteks bahasa secara lebih mendalam. karena keunggulannya dalam memproses hubungan antarkata secara bidirectional sehingga mampu menangkap pola linguistik yang tidak dapat ditangani metode tradisional. Dataset yang digunakan mencakup 3.807 berita politik berbahasa Indonesia yang telah diverifikasi sebagai fakta atau hoaks. Hasil penelitian menunjukkan bahwa BERT mencapai akurasi 98% dengan performa sangat baik pada kelas fakta dan cukup baik pada kelas hoaks. Temuan ini menegaskan bahwa BERT efektif digunakan untuk klasifikasi berita hoaks politik dan relevan sebagai dasar pengembangan sistem deteksi misinformasi berbasis NLP di masa mendatang.
Keywords
References
R. K. Kaliyar, A. Goswami, and P. Narang, “FakeBERT: Fake news detection in social media with a BERT-based deep learning approach,” Multimed Tools Appl, vol. 80, no. 8, pp. 11765–11788, Mar. 2021, doi: 10.1007/s11042-020-10183-2.
A. J. Keya, Md. A. H. Wadud, M. F. Mridha, M. Alatiyyah, and Md. A. Hamid, “AugFake-BERT: Handling Imbalance through Augmentation of Fake News Using BERT to Enhance the Performance of Fake News Classification,” Applied Sciences, vol. 12, no. 17, p. 8398, Aug. 2022, doi: 10.3390/app12178398.
N. Rai, D. Kumar, N. Kaushik, C. Raj, and A. Ali, “Fake News Classification using transformer based enhanced LSTM and BERT,” International Journal of Cognitive Computing in Engineering, vol. 3, pp. 98–105, June 2022, doi: 10.1016/j.ijcce.2022.03.003.
S. Minaee, N. Kalchbrenner, E. Cambria, N. Nikzad, M. Chenaghlu, and J. Gao, “Deep Learning--based Text Classification: A Comprehensive Review,” ACM Comput. Surv., vol. 54, no. 3, pp. 1–40, Apr. 2022, doi: 10.1145/3439726.
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.
J. Y. Khan, Md. T. I. Khondaker, S. Afroz, G. Uddin, and A. Iqbal, “A benchmark study of machine learning models for online fake news detection,” Machine Learning with Applications, vol. 4, p. 100032, June 2021, doi: 10.1016/j.mlwa.2021.100032.
R. K. Rahardi and S. Firda Utami, “Socio-political hoaxes in virtual public space: Assertive illocutionary manifestations of dishonesty in a critical pragmatics perspective,” BAHASTRA, vol. 44, no. 2, pp. 205–223, Oct. 2024, doi: 10.26555/bs.v44i2.998.
Technology Information and Industry Faculty, Stikubank University, Jl. Tri Lomba Juang No. 1, Semarang, Indonesia, J. S. Wibowo, E. N. Wahyudi, Vocational Faculty, Stikubank University, Jl. Kendeng V Bendan Ngisor, Semarang, Indonesia, H. Listiyono, and Vocational Faculty, Stikubank University, Jl. Kendeng V Bendan Ngisor, Semarang, Indonesia, “Performance Comparison of SVM, Naive Bayes, and Random Forest Models in Fake News Classification,” ETJ, vol. 09, no. 08, Aug. 2024, doi: 10.47191/etj/v9i08.27.
K. L. Tan, C. Poo Lee, and K. M. Lim, “Fake News Detection with Hybrid CNN-LSTM,” in 2021 9th International Conference on Information and Communication Technology (ICoICT), Yogyakarta, Indonesia: IEEE, Aug. 2021, pp. 606–610. doi: 10.1109/ICoICT52021.2021.9527469.
R. A. Sunan, H. F. E. K., and C. S. K. Aditya, “Klasifikasi Hoax Berita Politik Menggunakan Algoritma Long Short-Term Memory (LSTM) dengan Penambahan Fitur Embedding Global Vector (GloVe),” JEPIN, vol. 10, no. 2, p. 287, Aug. 2024, doi: 10.26418/jp.v10i2.76042.
L. Deping, W. Hongjuan, L. Mengyang, and L. Pei, “News text classification based on Bidirectional Encoder Representation from Transformers,” in 2021 International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA), Xi’an, China: IEEE, May 2021, pp. 137–140. doi: 10.1109/CAIBDA53561.2021.00036.
B. Sabiri, A. Khtira, B. El Asri, and M. Rhanoui, “Analyzing BERT’s Performance Compared to Traditional Text Classification Models:,” in Proceedings of the 25th International Conference on Enterprise Information Systems, Prague, Czech Republic: SCITEPRESS - Science and Technology Publications, 2023, pp. 572–582. doi: 10.5220/0011983100003467.
M. Guo, “Text classification by BERT-Capsules,” TE, vol. 1, no. 5, Feb. 2024, doi: 10.61173/wcg0nf17.
M. A. B. Al-Tarawneh, O. Al-irr, K. S. Al-Maaitah, H. Kanj, and W. H. F. Aly, “Enhancing Fake News Detection with Word Embedding: A Machine Learning and Deep Learning Approach,” Computers, vol. 13, no. 9, p. 239, Sept. 2024, doi: 10.3390/computers13090239.
G. Grunau and S. Linn, “Detection and Diagnostic Overall Accuracy Measures of Medical Tests,” Rambam Maimonides Med J, vol. 9, no. 4, p. e0027, Oct. 2018, doi: 10.5041/RMMJ.10351.
T. F. Monaghan et al., “Foundational Statistical Principles in Medical Research: Sensitivity, Specificity, Positive Predictive Value, and Negative Predictive Value,” Medicina, vol. 57, no. 5, p. 503, May 2021, doi: 10.3390/medicina57050503.
R. Yacouby and D. Axman, “Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models,” in Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems, Online: Association for Computational Linguistics, 2020, pp. 79–91. doi: 10.18653/v1/2020.eval4nlp-1.9.
Manuel Molina, “Un intruso de otro mundo: F1-score.,” Revista Electrónica AnestesiaR, vol. 16, no. 4, May 2024, doi: 10.30445/rear.v16i4.1258.
N. G. Ramadhan, F. D. Adhinata, A. J. T. Segara, and D. P. Rakhmadani, “Deteksi Berita Palsu Menggunakan Metode Random Forest dan Logistic Regression,” Jur. Ris. Kom., vol. 9, no. 2, p. 251, Apr. 2022, doi: 10.30865/jurikom.v9i2.3979.
Tushar Agarwal, Jitender Jangid, Gaurav Kumar, “Transformer and Natural language processing; A recent development.,” tjjpt, vol. 44, no. 1, pp. 140–143, Nov. 2023, doi: 10.52783/tjjpt.v44.i1.2225.
B. Juarto, “Classification of Hoax News Using Machine Learning and Neural Networks with BERT Embeddings,” in 2023 3rd International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS), Yogyakarta, Indonesia: IEEE, Aug. 2023, pp. 311–316. doi: 10.1109/ICE3IS59323.2023.10335413.
R. Qubra and R. A. Saputra, “Classification of Hoax News Using the Naïve Bayes Method,” ijsecs, vol. 4, no. 1, pp. 40–48, Apr. 2024, doi: 10.35870/ijsecs.v4i1.2068.
F. Ferawaty, M. Manullang, and R. Hanitio, “Fake News Classification Using SVM and Logistic Regression Methods,” in 2024 2nd International Conference on Technology Innovation and Its Applications (ICTIIA), Medan, Indonesia: IEEE, Sept. 2024, pp. 1–5. doi: 10.1109/ICTIIA61827.2024.10761435.
How To Cite This :
Refbacks
- There are currently no refbacks.
