Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jul 14;15(1):25436.
doi: 10.1038/s41598-025-05586-w.

Dual stream graph augmented transformer model integrating BERT and GNNs for context aware fake news detection

Hejamadi Rama Moorthy  1 , N J Avinash  2 , N S Krishnaraj Rao  3 , K R Raghunandan  4 , Radhakrishna Dodmane  5 , Jeremy Joseph Blum  6 , Lubna A Gabralla  7
Affiliations

Dual stream graph augmented transformer model integrating BERT and GNNs for context aware fake news detection

Hejamadi Rama Moorthy et al. Sci Rep. .

Abstract

The rapid proliferation of misinformation across digital platforms has highlighted the critical need for advanced fake news detection mechanisms. Traditional methods primarily rely on textual analysis, often neglecting the structural patterns of news dissemination, which play a crucial role in determining credibility. To address this limitation, this study proposes a Dual-Stream Graph-Augmented Transformer Model, integrating BERT for deep textual representation and Graph Neural Networks (GNNs) to model the propagation structure of misinformation. The objective is to enhance fake news detection by leveraging both linguistic and network-based features. The proposed method employs Graph Attention Networks (GAT) and Graph Transformers to extract contextual relationships, while an attention-based fusion mechanism effectively integrates textual and graph embeddings for classification. The model is implemented using PyTorch and Hugging Face Transformers, with experiments conducted on the FakeNewsNet dataset, which includes news articles, user interactions, and source metadata. Evaluation metrics such as accuracy, precision, recall, F1-score, and AUC-ROC indicate superior performance, with an accuracy of 99%, outperforming baseline models such as Bi-LSTM and RoBERTa-GCN. The study concludes that incorporating graph-based propagation features significantly improves fake news detection, providing a robust, scalable, and context-aware solution. Future enhancements will focus on refining credibility assessment mechanisms and extending the model to support multilingual and multimodal misinformation detection across diverse digital platforms.

Keywords: BERT; Context-Aware analysis; Fake news detection; Graph neural networks; Transformer model.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests. Consent to publish: All the authors are permitted to Consent to publish.

Figures

Fig. 1
Fig. 1
Workflow of the proposed BERT-GNN for fake news detection.
Fig. 2
Fig. 2
Workflow of pre-processing data.
Fig. 3
Fig. 3
Architecture of BERT.
Fig. 4
Fig. 4
(a) Attention mechanism (b) Multi-head attention.
Algorithm 1
Algorithm 1
Algorithm for dual-stream fake news detection model.
Fig. 5
Fig. 5
Flowchart of the proposed study.
Fig. 6
Fig. 6
Discriminatory words in news title.
Fig. 7
Fig. 7
Density distribution graph.
Fig. 8
Fig. 8
Graph visualization of news propagation.
Fig. 9
Fig. 9
Confusion matrix.
Fig. 10
Fig. 10
AUC-ROC curve.
Fig. 11
Fig. 11
Accuracy graph.
Fig. 12
Fig. 12
Loss graph.
Fig. 13
Fig. 13
A heatmap of attention weights.
Fig. 14
Fig. 14
ROC curve comparison.
Fig. 15
Fig. 15
Confusion matrix of BERT-GNN.
Fig. 16
Fig. 16
Confusion matrix of BERT.
Fig. 17
Fig. 17
Accuracy comparison graph.
Fig. 18
Fig. 18
Precision comparison graph.
Fig. 19
Fig. 19
Recall comparison graph.
Fig. 20
Fig. 20
F1-score comparison graph.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Alghamdi, J., Luo, S. & Lin, Y. A comprehensive survey on machine learning approaches for fake news detection. Multimed Tools Appl.83 (17), 51009–51067 (2024).
    1. Agarwal, A., Singh, Y. P. & Rai, V. Deciphering Deception: Unmasking Fake News in Multilingual Contexts, in IEEE International Conference on Computing, Power and Communication Technologies (IC2PCT), IEEE, 2024, pp. 807–812., IEEE, 2024, pp. 807–812. (2024).
    1. Olan, F., Jayawickrama, U., Arakpogun, E. O., Suklan, J. & Liu, S. Fake news on social media: the impact on society. Inf. Syst. Front.26 (2), 443–458 (2024). - PMC - PubMed
    1. Singh, M. K., Ahmed, J., Alam, M. A., Raghuvanshi, K. K. & Kumar, S. A comprehensive review on automatic detection of fake news on social media. Multimed Tools Appl.83 (16), 47319–47352 (2024).
    1. Olivera-Figueroa, L. A. & Bhattacharjee, U. The impact of misinformation, conspiracy theories, and fake news during the COVID-19 pandemic: what artificial intelligence can contribute to detect and mitigate their proliferation, in Handbook of Media Psychology: the Science and the Practice, Springer, 227–241. (2024).

LinkOut - more resources