A Hybrid Deep Learning Approach for Fake News Detection: Integrating XLNet, FastText, and CNN

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 1, pp. 60-66, January 2026.

https://doi.org/10.58482/ijersem.v2i1.9

This work is licensed under a Creative Commons Attribution 4.0 International License.

Full Text PDF

A Hybrid Deep Learning Approach for Fake News Detection: Integrating XLNet, FastText, and CNN

M.A.Manivasagam, M.Ritheesh, Kishan Kumar, Anand Kumar, Devarakonda Praveen Kumar, K Sravan Kumar

Department of CSE, Siddartha Institute of Science and Technology, Puttur, India.

Abstract: One of the serious trends is that misinformation has escalated a spectre of fake news and its consequences. Solving this challenge requires creating intelligent fake-news detection systems that use the specific algorithms needed to counter the fake-news threat. This paper seeks to improve the fake news detection procedure using the GPT-2 across CNN-LSTM models. For evaluation, we use a Kaggle dataset of real and fake news articles and compare the performance of existing detection algorithms with our recommended integrated architecture. To assess their performance, we fine-tune them on real news and retrain them on fake-news BERT, RoBERTa, FastText, and XLNet. Using GPT-2 for contextual feature extraction, along with CNN or LSTM networks for the other features, we improve classification accuracy over standard baseline models. The performance comparison analysis performed on real and fake news data show that the investigated hybrid model achieves higher accuracy in discriminating between real and fake news than previous models. This corroborates the possibility of integrating generative pre-trained transformers with standard deep learning models to enhance the robustness of a particular misinformation detection system.

Keywords: Fake News Detection, Misinformation, CNN-LSTM, BERT, Contextual Feature Extraction.

References: 

  1. M. Park and S. Chai, “Constructing a User-Centered Fake News Detection Model by Using Classification Algorithms in Machine Learning Techniques,” IEEE Access, vol. 11, pp. 71517–71527, 2023, doi: 10.1109/ACCESS.2023.3294613.
  2. C. Xu and M. T. Kechadi, “An Enhanced Fake News Detection System With Fuzzy Deep Learning,” IEEE Access, vol. 12, pp. 88006–88021, 2024, doi: 10.1109/ACCESS.2024.3418340.
  3. A. H. J. Almarashy, M. -R. Feizi-Derakhshi and P. Salehpour, “Enhancing Fake News Detection by Multi-Feature Classification,” in IEEE Access, vol. 11, pp. 139601-139613, 2023, doi: 10.1109/ACCESS.2023.3339621.
  4. N. Seddari, A. Derhab, M. Belaoued, W. Halboob, J. Al-Muhtadi, and A. Bouras, “A Hybrid Linguistic and Knowledge-Based Analysis Approach for Fake News Detection on Social Media,” IEEE Access, vol. 10, pp. 62097–62109, 2022, doi: 10.1109/ACCESS.2022.3181184.
  5. J. T. H. Kong, W. K. Wong, F. H. Juwono and C. Apriono, “Generating Fake News Detection Model Using A Two-Stage Evolutionary Approach,” in IEEE Access, vol. 11, pp. 85067-85085, 2023, doi: 10.1109/ACCESS.2023.3303321.
  6. Ravish, R. Katarya, D. Dahiya, and S. Checker, “Fake News Detection System Using Featured-Based Optimized MSVM Classification,” IEEE Access, vol. 10, pp. 113184–113199, 2022, doi: 10.1109/ACCESS.2022.3216892.
  7. M. Narra et al., “Selective Feature Sets Based Fake News Detection for COVID-19 to Manage Infodemic,” IEEE Access, vol. 10, pp. 98724–98736, 2022, doi: 10.1109/ACCESS.2022.3206963.
  8. G. K. Koru and Ç. Uluyol, “Detection of Turkish Fake News From Tweets With BERT Models,” in IEEE Access, vol. 12, pp. 14918-14931, 2024, doi: 10.1109/ACCESS.2024.3354165.
  9. A. Altheneyan and A. Alhadlaq, “Big Data ML-Based Fake News Detection Using Distributed Learning,” in IEEE Access, vol. 11, pp. 29447-29463, 2023, doi: 10.1109/ACCESS.2023.3260763.
  10. 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..
  11. Y. K. Zamil and N. M. Charkari, “Combating Fake News on Social Media: A Fusion Approach for Improved Detection and Interpretability,” IEEE Access, vol. 12, pp. 2074–2085, 2024, doi: 10.1109/ACCESS.2023.3342843.
  12. T. Jiang, J. P. Li, A. U. Haq, A. Saboor, and A. Ali, “A Novel Stacking Approach for Accurate Detection of Fake News,” IEEE Access, vol. 9, pp. 22626–22639, 2021, doi: 10.1109/ACCESS.2021.3056079.
Download PDF

This article is part of Volume 2, Issue 1 (January 2026)