★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★★Open research. Global perspectives.
tajssei@theamericanjournals.com Publisher Home ↗
Social Sciences OPEN ACCESS

An Analytical Study Of Hybrid Artificial Intelligence Techniques For Multi-Modal Fake News Detection

Asaad Makki Al-Ebadi
Higher Institute for Security and Administrative Development, Ministry of Interior, Iraq
Aqeel Luaibi Challoob
Department of Computer Techniques Engineering, Imam Alkadhim University College (IKU), Baghdad, 10001, Iraq
DOI Crossref DOI 10.37547/tajssei/Volume08Issue11-02
tajssei 2026
VOL. 8 / NO. 11 NOVEMBER
FULL TEXT PP. 12-28
PDF

View all articles in this issue ↗

VOLUME 8
ISSUE 11
YEAR 2026
PAGES 12-28
RESEARCH OVERVIEW

Abstract

Overview: The rapid growth of digital media has transformed news dissemination while enabling false information to spread widely, threatening information reliability and public trust. Automated fake news detection has consequently become an important research area, particularly where access is restricted to news headlines.

Research Problem: The research problem concerns accurately and reliably distinguishing fake from authentic news using headline content alone. Headlines provide limited contextual information and contain complex linguistic and semantic relationships that conventional statistical representations may inadequately capture. Additional challenges involve balancing predictive performance, generalizability, and computational cost while accommodating the changing nature of misinformation. These limitations motivate the investigation of complementary learning approaches within a consistent experimental framework.

Research Contributions: The study specifies a common headline-only framework for comparing SVM, XGBoost, CatBoost, BiLSTM, CNN–BiLSTM with Attention, RoBERTa, and DeBERTa. The proposed WELFake protocol assigns 60% of the stated 72,134 records to training, 20% to validation, and 20% to testing, with model-specific statistical, sequential, or contextual representations. A separate numerical illustration uses 10,000 generated observations, balanced between fake and authentic labels, to examine confusion matrices, accuracy, precision, recall, F1-score, and ROC–AUC. The illustration is not an evaluation of trained models on the WELFake test partition.

 

Research Conclusion: Within the generated-score analysis, the DeBERTa-labelled scenario records 94.78% accuracy, 94.79% F1-score, and 0.9889 ROC–AUC. These values follow the specified score distributions and do not establish empirical architectural superiority. Comparisons between SVM and CatBoost demonstrate that threshold-specific accuracy, positive-prediction reliability, and ranking discrimination can favour different scenarios. The study contributes a comparative protocol and a transparent interpretation of evaluation trade-offs. Verified held-out predictions, reproducible training configurations, and external evaluation are required before conclusions about WELFake performance, generalization, or deployment can be drawn.

RESEARCH TOPICS

Keywords

Fake News Detection News Headline Classification Machine Learning
SOURCES & SCHOLARSHIP

References

  1. M. M. Lawal and A. Abdulrauf, “Fake news detection using bi-lstm architecture: A deep learning approach on the isot dataset,” J. Comput. Theor. Appl., vol. 3, no. 2, pp. 104–114, 2025.
  2. F. A. Alshuwaier and F. A. Alsulaiman, “Fake news detection using machine learning and deep learning algorithms: A comprehensive review and future perspectives,” Computers, vol. 14, no. 9, p. 394, 2025.
  3. M. Nasser et al., “A systematic review of multimodal fake news detection on social media using deep learning models,” Results Eng., vol. 26, p. 104752, 2025.
  4. J. Alghamdi, Y. Lin, and S. Luo, “A comparative study of machine learning and deep learning techniques for fake news detection,” Information, vol. 13, no. 12, p. 576, 2022.
  5. A. K. Yadav et al., “Fake news detection using hybrid deep learning method,” SN Comput. Sci., vol. 4, no. 6, p. 845, 2023.
  6. 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.
  7. M. A. B. Al-Tarawneh, O. Al-Irr, K. S. Al-Maaitah, H. Kanj, and W. H. F. Aly, “Enhancing fake news detection with word embedding: A machine learning and deep learning approach,” Computers, vol. 13, no. 9, p. 239, 2024.
  8. H. Padalko, V. Chomko, and D. Chumachenko, “A novel approach to fake news classification using LSTM-based deep learning models,” Front. big Data, vol. 6, p. 1320800, 2024.
  9. D. Mouratidis, A. Kanavos, and K. Kermanidis, “From misinformation to insight: Machine learning strategies for fake news detection,” Information, vol. 16, no. 3, p. 189, 2025.
  10. J. Alghamdi, Y. Lin, and S. Luo, “Machine learning and deep learning approaches for fake news detection and related topics in multilingual contexts: A systematic literature review,” Multimed. Tools Appl., vol. 85, no. 4, p. 353, 2026.
  11. Y. Tian, S. Xu, Y. Cao, Z. Wang, and Z. Wei, “An empirical comparison of machine learning and deep learning models for automated fake news detection,” Mathematics, vol. 13, no. 13, p. 2086, 2025.
  12. S. Bird, E. Klein, and E. Loper, Natural language processing with Python: analyzing text with the natural language toolkit . “ O’Reilly Media, Inc.,” 2009.
  13. A. Tabassum and R. R. Patil, “A survey on text pre-processing & feature extraction techniques in natural language processing,” Int. Res. J. Eng. Technol. , vol. 7, no. 06, pp. 4864–4867, 2020.
  14. S. Selva Birunda and R. Kanniga Devi, “A review on word embedding techniques for text classification,” Innov. Data Commun. Technol. Appl. Proc. ICIDCA 2020 , pp. 267–281, 2021.
  15. L. Abualigah, Y. Y. Al-Ajlouni, M. S. Daoud, M. Altalhi, and H. Migdady, “Fake news detection using recurrent neural network based on bidirectional LSTM and GloVe,” Soc. Netw. Anal. Min. , vol. 14, no. 1, p. 40, 2024.
  16. A. A. Pal, S. Mondal, C. A. Kumar, and C. J. Kumar, “A transformer-based approach for fake news and spam detection in social media using roberta,” in 2025 International Conference on Multi-Agent Systems for Collaborative Intelligence (ICMSCI) , IEEE, 2025, pp. 1256–1263.
  17. S. Sweidan, N. A. Farouk, M. Abouhawwash, S. S. Askar, and M. Taha, “DeBERTa-based framework for detecting machine-generated content on social media: a comparative study,” J. Big Data , vol. 13, no. 1, p. 10, 2026.
  18. M. Sudhakar and K. P. Kaliyamurthie, “Detection of fake news from social media using support vector machine learning algorithms,” Meas. Sensors , vol. 32, p. 101028, 2024.
  19. J. Subramanian, G. J. Sendur, P. Adithiyan, S. P. Kumar, S. M. Kumar, and M. R. Kumar, “Enhancing fake news detection: A comprehensive framework leveraging XGBoost and CNNs,” in 2024 3rd International conference on artificial intelligence for internet of things (AIIoT) , IEEE, 2024, pp. 1–6.
  20. U. Gupta, S. Raj, and J. B. Pernabas, “Optimized Fake News Detection in Social Networks Using Boosting Algorithms and Machine Learning Classifiers,” in International Conference on Computing and Machine Learning , Springer, 2025, pp. 275–287.
  21. J. Alghamdi, Y. Lin, and S. Luo, “Modeling fake news detection using bert-cnn-bilstm architecture,” in 2022 IEEE 5th international conference on multimedia information processing and retrieval (MIPR) , IEEE, 2022, pp. 354–357.
  22. P. Resnik and J. Lin, “11 evaluation of NLP systems,” Handb. Comput. Linguist. Nat. Lang. Process. , vol. 57, 2010.
  23. Sideek, Shirin Muataz Mohammed, et al. "An Improved Anomaly-based Intrusion Detection System for IoT Applications using Machine Learning Methods." Pertanika Journal of Science & Technology 34.1 (2026): 401.‏
  24. Nuimi, Zeina N., et al. "Decoupling Transient from Steady-state Performance in Fractional-order PI Control of a DC Microgrid: A Bi-objective Formulation Validated Against Single-metric and Recent-metaheuristic Benchmarks." Int. J. Intell. Eng. Syst 19.9 (2026): 337.‏
  25. Yaseen, Nabeel Abdulrazaq, et al. "Enhancing Road Safety through Advanced Machine Learning: A Comparative Study of Tree Ensembles, Neural Networks, and Integrated Models for Multi-class Accident Severity Prediction under Class Imbalance." Int. J. Intell. Eng. Syst 19.9 (2026): 467.‏
  26. Ahmed, Asraa Safaa, et al. "An accurate model for text document classification using machine learning techniques." Ing. des Syst. d’Information 30.4 (2025): 913-921.‏
  27. Jabbar, Noor Kareem, Majn Naderan, and Mustafa Sabah Taha. "HybridIoMT: A Dual-Phase Machine Learning Framework for Robust Cybersecurity in Internet of Medical Things." International Journal of Intelligent Engineering & Systems 18.4 (2025): 307.‏
  28. Ahmed, Attallah Salih, Israa Nasir Abood, and Mustafa Sabah Taha. "Adaptive Multi-objective Optimization for Obstacle-aware Wireless Sensor Network Deployment: A Comparative Analysis of State-of-the-Art Algorithms." International Journal of Intelligent Engineering & Systems 19.2 (2026): 707.‏
  29. Ismael, Bahaa Muneer, et al. "Non-dominated sorting genetic algorithm for channel assignment in multiple radio interfaces with multiple channels." AIP Conference Proceedings. Vol. 3393. No. 1. AIP Publishing LLC, 2026.‏
  30. Ismael, Bahaa Muneer, et al. "Multi-Agent Reinforcement Learning for User-Router Assignment in Multi-Radio Multi-Channel Wireless Mesh Networks." International Journal of Intelligent Engineering & Systems 18.8 (2025): 316.‏
  31. P. K. Verma, P. Agrawal, I. Amorim, and R. Prodan, “WELFake: Word embedding over linguistic features for fake news detection,” IEEE Trans. Comput. Soc. Syst. , vol. 8, no. 4, pp. 881–893, 2021.