Identifikasi Berita Palsu di Portal Media Online Menggunakan Model IndoBERT dan LSTM

Angga Mochamad Kamal; Yulison Herry Chrisnanto; Rezki Yuniarti

doi:10.30865/jurikom.v12i3.8660

Authors

Angga Mochamad Kamal Universitas Jenderal Achmad Yani, Cimahi
Yulison Herry Chrisnanto Universitas Jenderal Achamad Yani, Cimahi
Rezki Yuniarti Universitas Jenderal Achmad Yani, Cimahi

DOI:

https://doi.org/10.30865/jurikom.v12i3.8660

Keywords:

Fake News, IndoBERT, LSTM, Ensemble Stacking, Automatic Detection

Abstract

The rapid spread of political fake news on Indonesian online media portals poses serious threats to public trust and democratic stability. The main research problem is the limitation of existing models in handling the complexity of Indonesian political narratives containing local idioms and long text structures. The proposed solution employs a hybrid IndoBERT-LSTM model with ensemble stacking approach using logistic regression meta-learner to optimize fake news detection. IndoBERT is selected to capture Indonesian language nuances, while LSTM handles sequential dependencies in long articles. The research objective is to develop an accurate detection system for political fake news by leveraging the complementary strengths of both models. The dataset comprises 32,218 political articles from credible portals (Kompas, CNN Indonesia, Tempo, Detiknews, Viva) and Turnbackhoax.id validation from September 2021 to December 2024. Research results demonstrate that ensemble stacking achieves superior performance with F1-score 0.9544, accuracy 95.41%, and AUC-ROC 0.9936, outperforming standalone IndoBERT (F1: 0.9542) and LSTM (F1: 0.9417). Error analysis identifies 4.59% error rate with 134 false positives and 88 false negatives, particularly in long articles (average 2,739 characters). This model has potential for integration into fact-checking platforms for real-time detection of Indonesian political fake news.

References

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.

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,” vol. 21, no. 2, pp. 693–7554, 2024, doi: 10.33751/komputasi.v21i2.5260.

A. Tasnim, Md. Saiduzzaman, M. A. Rahman, J. Akhter, and A. S. Md. M. Rahaman, “Performance Evaluation of Multiple Classifiers for Predicting Fake News,” Journal of Computer and Communications, vol. 10, no. 09, pp. 1–21, 2022, doi: 10.4236/jcc.2022.109001.

V. Prisscilya and A. S. Girsang, “Classification of Indonesia False News Detection Using Bertopic and Indobert,” Jurnal Indonesia Sosial Teknologi, vol. 5, no. 8, 2024, [Online]. Available: http://jist.publikasiindonesia.id/

F. K. Alarfaj and J. A. Khan, “Deep Dive into Fake News Detection: Feature-Centric Classification with Ensemble and Deep Learning Methods,” Algorithms, vol. 16, no. 11, Nov. 2023, doi: 10.3390/a16110507.

S. William, Kenny, and A. Chowanda, “EMOTION RECOGNITION INDONESIAN LANGUAGE FROM TWITTER USING INDOBERT AND BI-LSTM,” Communications in Mathematical Biology and Neuroscience, vol. 2024, 2024, doi: 10.28919/cmbn/7858.

Muhammad Ikram Kaer Sinapoy, Yuliant Sibaroni, and Sri Suryani Prasetyowati, “Comparison of LSTM and IndoBERT Method in Identifying Hoax on Twitter,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 3, pp. 657–662, Jun. 2023, doi: 10.29207/resti.v7i3.4830.

M. A. Khder, “Web scraping or web crawling: State of art, techniques, approaches and application,” International Journal of Advances in Soft Computing and its Applications, vol. 13, no. 3, pp. 144–168, 2021, doi: 10.15849/ijasca.211128.11.

M. Anusha and R. Leelavathi, “Hybrid Approach to Fake News Detection: Leveraging BERT-Based Model with Word Embedding Features for Sentiment Classification in Social Media Content,” 2024.

S. Rahmawati, “DETEKSI BERITA HOAX PADA WEBSITE TURNBACKHOAX DENGAN PROGRAM STUDI MATEMATIKA,” 2021.

S. M. Sr and S. Ahmad, “BERT based Blended approach for Fake News Detection,” Journal of Big Data and Artificial Intelligence, vol. 2, no. 1, Jan. 2024, doi: 10.54116/jbdai.v2i1.27.

E. Essa, K. Omar, and A. Alqahtani, “Fake news detection based on a hybrid BERT and LightGBM models,” Complex and Intelligent Systems, vol. 9, no. 6, pp. 6581–6592, Dec. 2023, doi: 10.1007/s40747-023-01098-0.

A. A. Kurniawan and M. Mustikasari, “Implementasi Deep Learning Menggunakan Metode CNN dan LSTM untuk Menentukan Berita Palsu dalam Bahasa Indonesia,” vol. 5, no. 4, pp. 2622–4615, 2020, doi: 10.32493/informatika.v5i4.7760.

A. J. Keya, H. H. Shajeeb, M. S. Rahman, and M. F. Mridha, “FakeStack: Hierarchical Tri-BERT-CNN-LSTM stacked model for effective fake news detection,” PLoS One, vol. 18, no. 12 December, Dec. 2023, doi: 10.1371/journal.pone.0294701.

A. M. Ali, F. A. Ghaleb, B. A. S. Al-Rimy, F. J. Alsolami, and A. I. Khan, “Deep Ensemble Fake News Detection Model Using Sequential Deep Learning Technique,” Sensors, vol. 22, no. 18, Sep. 2022, doi: 10.3390/s22186970.

E. Hashmi, S. Y. Yayilgan, M. M. Yamin, S. Ali, and M. Abomhara, “Advancing Fake News Detection: Hybrid Deep Learning With FastText and Explainable AI,” IEEE Access, vol. 12, pp. 44462–44480, 2024, doi: 10.1109/ACCESS.2024.3381038.

P. Singh, R. Srivastava, K. P. S. Rana, and V. Kumar, “SEMI-FND: Stacked Ensemble Based Multimodal Inference For Faster Fake News Detection,” 2023. [Online]. Available: www.nsut.ac.in

M. E Almandouh, M. F. Alrahmawy, M. Eisa, M. Elhoseny, and A. S. Tolba, “Ensemble based high performance deep learning models for fake news detection,” Sci Rep, vol. 14, no. 1, p. 26591, Dec. 2024, doi: 10.1038/s41598-024-76286-0.

J. Howard and S. Gugger, “Deep Learning for Coders with fastai & PyTorch AI Applications Without a PhD TM,” 2020.

F. Fleuret, “The Little Book of Deep Learning,” 2023.

M. S. Toor et al., “An Optimized Weighted-Voting-Based Ensemble Learning Approach for Fake News Classification,” Mathematics, vol. 13, no. 3, Feb. 2025, doi: 10.3390/math13030449.

A. A. Khan, O. Chaudhari, and R. Chandra, “A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation,” Jun. 15, 2024, Elsevier Ltd. doi: 10.1016/j.eswa.2023.122778.