A HYBRID BERT–GNN FOR DETECTING HOAXES AND NEGATIVE CONTENT IN INDONESIAN SOCIAL MEDIA
DOI:
https://doi.org/10.33480/jitk.v11i3.7330Keywords:
BERT, Deep Learning, Graph Neural Network, Hoax, Negative ContentAbstract
The rapid spread of hoaxes on social media threatens public trust and information integrity, especially within the Indonesian digital landscape. This study proposes a hybrid deep learning model that integrates transformer-based semantic representation from IndoBERT with Graph Neural Networks (GNNs) to enhance hoax detection performance. A heterogeneous social graph is constructed to model relationships among posts, users, and news sources, where post node features are extracted from the [CLS] embeddings of a fine-tuned IndoBERT. The GNN component consists of two graph convolutional layers with ReLU activation and dropout, followed by a multilayer perceptron classifier for binary classification. Experiments conducted on the Indonesia False News dataset (Kaggle) employ SMOTE resampling to handle class imbalance and 5-fold stratified cross-validation for robust evaluation across three configurations: BERT-only, GNN-only, and the proposed BERT–GNN hybrid model. The hybrid model achieves an average F1-score of 0.89 ± 0.01 and ROC-AUC of 0.92 ± 0.01, outperforming both single-model baselines while maintaining a balanced precision–recall trade-off. These results confirm that combining contextual semantic understanding with relational graph topology substantially enhances accuracy, robustness, and generalization in detecting hoaxes within Indonesian-language social media content
Downloads
References
[1] M. F. Mridha, A. J. Keya, M. A. Hamid, M. M. Monowar, and M. S. Rahman, “A Comprehensive Review on Fake News Detection With Deep Learning,” IEEE Access, vol. 9, pp. 156151–156170, 2021, doi: 10.1109/ACCESS.2021.3129329.
[2] M. A. Wani et al., “Toxic Fake News Detection and Classification for Combating COVID-19 Misinformation,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 4, pp. 5101–5118, 2024, doi: 10.1109/TCSS.2023.3276764.
[3] A. Rahmawati, A. Alamsyah, and A. Romadhony, “Hoax News Detection Analysis using IndoBERT Deep Learning Methodology,” 2022 10th Int. Conf. Inf. Commun. Technol. ICoICT 2022, no. August 2022, pp. 368–373, 2022, doi: 10.1109/ICoICT55009.2022.9914902.
[4] V. Maniyal and V. Kumar, “Unveiling the Deepfake Dilemma: Framework, Classification, and Future Trajectories,” IT Prof., vol. 26, no. 2, pp. 32–38, 2024, doi: 10.1109/MITP.2024.3369948.
[5] M. Nirav Shah and A. Ganatra, “A systematic literature review and existing challenges toward fake news detection models,” Soc. Netw. Anal. Min., vol. 12, no. 1, pp. 1–21, 2022, doi: 10.1007/s13278-022-00995-5.
[6] S. A. Aljawarneh and S. A. Swedat, “Fake News Detection Using Enhanced BERT,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 4, pp. 4843–4850, 2024, doi: 10.1109/TCSS.2022.3223786.
[7] J. A. Reshi and R. Ali, “An Efficient Fake News Detection System Using Contextualized Embeddings and Recurrent Neural Network,” Int. J. Interact. Multimed. Artif. Intell., vol. 8, no. 6, pp. 38–50, 2024, doi: 10.9781/ijimai.2023.02.007.
[8] J. Choi, T. Ko, Y. Choi, H. Byun, and C. Kim, “Dynamic graph convolutional networks with attention mechanism for rumor detection on social media,” PLoS One, vol. 16, no. 8, p. e0256039, Aug. 2021, [Online]. Available: https://doi.org/10.1371/journal.pone.0256039
[9] T. H. Do, M. Berneman, J. Patro, G. Bekoulis, and N. Deligiannis, “Context-Aware Deep Markov Random Fields for Fake News Detection,” IEEE Access, vol. 9, pp. 130042–130054, 2021, doi: 10.1109/ACCESS.2021.3113877.
[10] S. Ni, J. Li, and H.-Y. Kao, “MVAN: Multi-View Attention Networks for Fake News Detection on Social Media,” IEEE Access, vol. 9, pp. 106907–106917, 2021, doi: 10.1109/ACCESS.2021.3100245.
[11] Z. Qu, F. Zhou, X. Song, R. Ding, L. Yuan, and Q. Wu, “Temporal Enhanced Multimodal Graph Neural Networks for Fake News Detection,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 6, pp. 7286–7298, 2024, doi: 10.1109/TCSS.2024.3404921.
[12] S. Kuntur, M. Krzywda, A. Wróblewska, M. Paprzycki, and M. Ganzha, “Comparative Analysis of Graph Neural Networks and Transformers for Robust Fake News Detection: A Verification and Reimplementation Study,” Electronics, vol. 13, no. 23, 2024, doi: 10.3390/electronics13234784.
[13] J. Alghamdi, Y. Lin, and S. Luo, “Towards COVID-19 fake news detection using transformer-based models,” Knowledge-Based Syst., vol. 274, p. 110642, 2023, doi: 10.1016/j.knosys.2023.110642.
[14] 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.
[15] A. S. Karnyoto, C. Sun, B. Liu, and X. Wang, “Transfer Learning and GRU-CRF Augmentation for Covid-19 Fake News Detection,” Comput. Sci. Inf. Syst., vol. 19, no. 2, pp. 639–658, 2022, doi: 10.2298/CSIS210501053K.
[16] Z. Guo, K. Yu, A. Jolfaei, G. Li, F. Ding, and A. Beheshti, “Mixed Graph Neural Network-Based Fake News Detection for Sustainable Vehicular Social Networks,” IEEE Trans. Intell. Transp. Syst., vol. 24, no. 12, pp. 15486–15498, 2023, doi: 10.1109/TITS.2022.3185013.
[17] H. Che, B. Pan, M.-F. Leung, Y. Cao, and Z. Yan, “Tensor Factorization With Sparse and Graph Regularization for Fake News Detection on Social Networks,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 4, pp. 4888–4898, 2024, doi: 10.1109/TCSS.2023.3296479.
[18] N. Ahuja and S. Kumar, “Fusion of Semantic, Visual and Network Information for Detection of Misinformation on Social Media,” Cybern. Syst., vol. 55, no. 5, pp. 1063–1085, Jul. 2024, doi: 10.1080/01969722.2022.2130248.
[19] Y. Jang, C. H. Park, D. G. Lee, and Y. S. Seo, “Fake News Detection on Social Media: A Temporal-Based Approach,” Comput. Mater. Contin., vol. 69, no. 3, pp. 3564–3580, 2021, doi: 10.32604/cmc.2021.018901.
[20] J. V. Tembhurne, M. M. Almin, and T. Diwan, “Mc-DNN: Fake News Detection Using Multi-Channel Deep Neural Networks,” Int. J. Semant. Web Inf. Syst., vol. 18, no. 1, pp. 1–20, 2022, doi: 10.4018/IJSWIS.295553.
[21] P. N. Andono and R. A. Pramunendar, “Performance Evaluation of Classification Algorithm for Movie Review Sentiment Analysis,” Int. J. Comput., vol. 22, no. 1, pp. 7–14, 2023, doi: 10.47839/ijc.22.1.2873.
[22] B. A. Prakoso, A. Z. Fanani, I. Riawan, and H. Fajri, “Word Search with Trending Reviews on Twitter,” Ingénierie des Systèmes d’Information, vol. 28, no. 2, pp. 351–356, 2023, [Online]. Available: https://doi.org/10.18280/isi.280210
[23] S. Fitria, 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,” arXiv Prepr. arXiv2308.04950, pp. 1–6, 2023, [Online]. Available: https://github.com/Shafna81/fakenewsdetection.git
[24] H. Zhao, J. Xie, and H. Wang, “Graph Convolutional Network Based on Multi-Head Pooling for Short Text Classification,” IEEE Access, vol. 10, no. 1, pp. 11947–11956, 2022, doi: 10.1109/ACCESS.2022.3146303.
[25] R. Akula and I. Garibay, “Interpretable multi-head self-attention architecture for sarcasm detection in social media,” Entropy, vol. 23, no. 4, 2021, doi: 10.3390/e23040394.
[26] S. Benslimane, J. Azé, S. Bringay, M. Servajean, and C. Mollevi, “A text and GNN based controversy detection method on social media,” World Wide Web, vol. 26, no. 2, pp. 799–825, 2023, doi: 10.1007/s11280-022-01116-0.
[27] Z. Sutriawan, Muljono, Khairunnisa, Alamin, T. A. Lorosae, and S. Ramadhan, “Improving Performance Sentiment Movie Review Classification Using Hybrid Feature TFIDF , N-Gram , Information Gain and Support Vector Machine,” Math. Model. Eng. Probl., vol. 11, no. 2, pp. 375–384, 2024.
[28] M. Heydarian, T. E. Doyle, and R. Samavi, “MLCM: Multi-Label Confusion Matrix,” IEEE Access, vol. 10, pp. 19083–19095, 2022, doi: 10.1109/ACCESS.2022.3151048.
[29] H. Karande, R. Walambe, V. Benjamin, K. Kotecha, and T. S. Raghu, “Stance detection with BERT embeddings for credibility analysis of information on social media,” PeerJ Comput. Sci., vol. 7, pp. 1–20, 2021, doi: 10.7717/peerj-cs.467.
[30] L. S. Moreira, G. M. Lunardi, M. de O. Ribeiro, W. Silva, and F. P. Basso, “A Study of Algorithm-Based Detection of Fake News in Brazilian Election: Is BERT the Best,” IEEE Lat. Am. Trans., vol. 21, no. 8, pp. 897–903, 2023, doi: 10.1109/TLA.2023.10246346.
[31] 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, Nov. 2024, doi: 10.1038/s41598-024-76286-0.
[32] R. K. Kaliyar, A. Goswami, P. Narang, and V. Chamola, “Understanding the Use and Abuse of Social Media: Generalized Fake News Detection With a Multichannel Deep Neural Network,” IEEE Trans. Comput. Soc. Syst., vol. 11, no. 4, pp. 4878–4887, 2024, doi: 10.1109/TCSS.2022.3221811.
[33] 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, 2021, doi: 10.1007/s11042-020-10183-2.
[34] A. Malik, D. Kumar, J. Hota, and A. Ratna, “Results in Engineering Ensemble graph neural networks for fake news detection using user engagement and text features,” Results Eng., vol. 24, no. June, p. 103081, 2024, doi: 10.1016/j.rineng.2024.103081
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Khairunnisa, Khairunnas, Sutriawan
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
