Deteksi Berita Hoaks Berbahasa Indonesia yang Dapat Dijelaskan Menggunakan IndoBERT dan SHAP
Muhammad Hasraddin Hasnan(1); Rizky Yusliana Bakti(2); Muhammad Faisal(3*); Titik Khawa Abd Rahman(4); Nurnawaty Nurnawaty(5); Muhammad Syafaat S. Kuba(6); Titin Wahyuni(7);
(1) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(2) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(3) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(4) School Science and Technology, Asia E University, Selangor, Malaysia
(5) Teknik Pengairan, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(6) Teknik Pengairan, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(7) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(*) Corresponding Author
AbstractPerkembangan teknologi informasi dan media sosial telah mempercepat penyebaran berita palsu, sehingga diperlukan sistem deteksi yang akurat, andal, dan mudah diinterpretasikan. Penelitian ini bertujuan mengembangkan sistem deteksi fake news berbahasa Indonesia dengan mengintegrasikan IndoBERT sebagai model klasifikasi teks dan SHAP sebagai pendekatan Explainable Artificial Intelligence (XAI) untuk menjelaskan kontribusi kata terhadap hasil prediksi. Dataset diperoleh dari TurnBackHoax dan Kaggle, kemudian melalui tahapan preprocessing berupa cleaning text, filtering bahasa Indonesia, tokenisasi, serta penyeimbangan data menggunakan random oversampling pada data latih. Dari 5.347 data awal, diperoleh 4.980 data setelah filtering bahasa Indonesia, terdiri atas 3.613 data valid dan 1.367 data hoaks. Data dibagi secara stratifikasi dengan rasio 80% untuk pelatihan dan 20% untuk pengujian. Setelah oversampling, data latih menjadi seimbang dengan masing-masing 2.890 sampel per kelas. Hasil eksperimen menunjukkan bahwa model baseline TF-IDF dan Logistic Regression memperoleh akurasi 77%, sedangkan IndoBERT mencapai akurasi 87%, dengan precision 0,87, recall 0,95, dan F1-score 0,91 pada kelas hoaks. Visualisasi SHAP menunjukkan token penting yang memengaruhi klasifikasi. Hasil ini membuktikan bahwa integrasi IndoBERT dan SHAP efektif meningkatkan deteksi berita palsu sekaligus memberikan transparansi model.
KeywordsDeteksi Berita Hoaks; IndoBERT; SHAP; Explainable AI; Klasifikasi Teks
|
Full Text:PDF |
Article MetricsAbstract view: 61 timesPDF view: 23 times |
Digital Object Identifier https://doi.org/10.33096/busiti.v7i2.3466
|
Cite |
References
M. U. G. Khan, A. Mehmood, M. Elhadef, and S. A. Chaudhry, “Fake News Classification: Past, Current, and Future,” Comput. Mater. Contin., vol. 77, no. 2, pp. 2225–2249, Nov. 2023, doi: 10.32604/CMC.2023.038303.
A. Saeed and E. Al Solami, “Fake News Detection Using Machine Learning and Deep Learning Methods,” Comput. Mater. Contin., vol. 77, no. 2, pp. 2079–2096, Nov. 2023, doi: 10.32604/CMC.2023.030551.
H. D. Nguyen and T. Le, “Explainable Fake News Detection via Multi-Aspect Semantic Discovery,” Procedia Comput. Sci., vol. 270, pp. 3211–3220, 2025, doi: 10.1016/j.procs.2025.09.446.
C. Zhang, A. Gupta, X. Qin, and Y. Zhou, “A computational approach for real-time detection of fake news,” Expert Syst. Appl., vol. 221, p. 119656, Jul. 2023, doi: 10.1016/J.ESWA.2023.119656.
A. J. Dal Forno, G. P. Richetti, and V. H. Knaesel, “Fake news detection algorithms – A systematic literature review,” Data Knowl. Eng., vol. 158, p. 102441, Jul. 2025, doi: 10.1016/J.DATAK.2025.102441.
R. K. Gurjwar, A. Kumar, and U. P. Rao, “EPRVFL: A fast and scalable model for real-time fake news detection,” Pattern Recognit. Lett., vol. 196, pp. 267–273, Oct. 2025, doi: 10.1016/J.PATREC.2025.06.006.
L. A. Pekandi, R. G. Widjaja, A. Ananta, J. Harefa, and K. Jingga, “Evaluating IndoBERT for Indonesian Hoax News Detection: A Comparative Study with Ensemble and CNN-LSTM Models,” Procedia Comput. Sci., vol. 269, pp. 1625–1633, 2025, doi: 10.1016/j.procs.2025.09.105.
A. B. Athira, S. D. M. Kumar, and A. M. Chacko, “A systematic survey on explainable AI applied to fake news detection,” Eng. Appl. Artif. Intell., vol. 122, p. 106087, Jun. 2023, doi: 10.1016/J.ENGAPPAI.2023.106087.
Z. Zhang et al., “GBCA: Graph Convolution Network and BERT combined with Co-Attention for fake news detection,” Pattern Recognit. Lett., vol. 180, pp. 26–32, Apr. 2024, doi: 10.1016/J.PATREC.2024.02.014.
K. Yu, S. Jiao, and Z. Ma, “Fake News Detection Based on BERT Multi-domain and Multi-modal Fusion Network,” Comput. Vis. Image Underst., vol. 252, p. 104301, Feb. 2025, doi: 10.1016/J.CVIU.2025.104301.
Q. Zhang, X. Weng, G. Zhou, Y. Zhang, and J. X. Huang, “ARL: An adaptive reinforcement learning framework for complex question answering over knowledge base,” Inf. Process. Manag., vol. 59, no. 3, p. 102933, May 2022, doi: 10.1016/J.IPM.2022.102933.
G. Folino, M. Guarascio, L. Pontieri, and P. Zicari, “Discovering ensembles of small language models out of scarcely labelled data for fake news detection,” Appl. Soft Comput., vol. 171, no. January, p. 112794, 2025, doi: 10.1016/j.asoc.2025.112794.
M. Han, J. Li, Y. Chen, L. Xu, and L. Tao, “EC-Fake: A fake news detection model based on external knowledge and contrast-driven feature augmentation,” Neurocomputing, vol. 653, p. 131214, Nov. 2025, doi: 10.1016/J.NEUCOM.2025.131214.
M. Han, J. Li, S. Ou, L. Xu, and L. Tao, “ET-Fake: A multi-modal fake news detection model augmented with external knowledge and two-stage feature fusion,” Appl. Soft Comput., vol. 188, p. 114392, Feb. 2026, doi: 10.1016/J.ASOC.2025.114392.
Amandeep and S. Suresh, “Transforming Fake News Detection: Leveraging DistilBERT Models for Enhanced Accuracy,” Procedia Comput. Sci., vol. 260, pp. 283–290, 2025, doi: 10.1016/j.procs.2025.03.203.
B. Xie and Q. Li, “Detecting fake news by RNN-based gatekeeping behavior model on social networks,” Expert Syst. Appl., vol. 231, p. 120716, Nov. 2023, doi: 10.1016/J.ESWA.2023.120716.
R. Anju and N. Pervin, “CredBERT: Credibility-aware BERT model for fake news detection,” Data Knowl. Eng., vol. 160, p. 102461, Nov. 2025, doi: 10.1016/J.DATAK.2025.102461.
R. N. Tanaja, Johnny, M. A. Rafif, and A. A. S. Gunawan, “Fake News Detection using Machine Learning: Integrating FakeBERT Classification, Style Analysis, and Credibility Verification,” Procedia Comput. Sci., vol. 269, pp. 1067–1076, 2025, doi: 10.1016/j.procs.2025.09.048.
A. Rahman, S. Zaman, S. Parvej, P. C. Shill, M. S. Salim, and D. Das, “Fake News Detection: Exploring the Efficiency of Soft and Hard Voting Ensemble,” Procedia Comput. Sci., vol. 252, pp. 748–757, 2025, doi: 10.1016/j.procs.2025.01.035.
R. Mohawesh, X. Liu, H. M. Arini, Y. Wu, and H. Yin, “Semantic graph based topic modelling framework for multilingual fake news detection,” AI Open, vol. 4, no. June, pp. 33–41, 2023, doi: 10.1016/j.aiopen.2023.08.004.
E. Raja, B. Soni, and S. K. Borgohain, “Fake news detection in Dravidian languages using multiscale residual CNN_BiLSTM hybrid model,” Expert Syst. Appl., vol. 250, p. 123967, Sep. 2024, doi: 10.1016/J.ESWA.2024.123967.
H. Jin and P. Wang, “Fake news detection on social media using triple-attention mechanism optimized by advanced tailor optimization algorithm,” Egypt. Informatics J., vol. 32, no. November, p. 100815, 2025, doi: 10.1016/j.eij.2025.100815.
P. Dhiman, A. Kaur, D. Gupta, S. Juneja, A. Nauman, and G. Muhammad, “GBERT: A hybrid deep learning model based on GPT-BERT for fake news detection,” Heliyon, vol. 10, no. 16, p. e35865, 2024, doi: 10.1016/j.heliyon.2024.e35865.
K. S. Sreekar Datta, G. Narasimha Naidu, S. Abhishek, and T. Anjali, “Enhancing Veracity: Empirical Evaluation of Fake News Detection Techniques,” Procedia Comput. Sci., vol. 233, pp. 97–107, Jan. 2024, doi: 10.1016/J.PROCS.2024.03.199.
J. Alghamdi, Y. Lin, and S. Luo, “ABERT: Adapting BERT model for efficient detection of human and AI-generated fake news,” Int. J. Inf. Manag. Data Insights, vol. 5, no. 2, p. 100353, 2025, doi: 10.1016/j.jjimei.2025.100353.
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Buletin Sistem Informasi dan Teknologi Islam (BUSITI)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.