Citation :

Ramoni Tirimisiyu Amosa, Adekiigbe Adebanjo, Fabiyi Aderanti Alifat, Olorunlomerue Adam Biodun, Adisa Solagbade Philip, Lawal Moshood Olatunji, Akanni Abideen Amosa, "Comparative Analysis of Machine Learning Models with SHAP Explanations towards Transparent Fake News Detection," International Journal of Computer Science and Engineering, vol. 13, no. 9, pp. 1-10, 2026. Crossref, https://doi.org/10.14445/23488387/IJCSE-V13I9P101

Abstract

The generation of fake news on online platforms has grown into a serious problem, compromising public trust, public opinion and the possibility of information-based decision making. In this study, an intelligent Fake News Detection (FND) system to automatically classify news articles as fake or real was developed using techniques of Natural Language Processing (NLP), Machine Learning (ML) and Explainable Artificial Intelligence (XAI). A publicly available dataset consisting of 44,856 news articles from the LIAR data set and the Kaggle repository was used, of which 80% was used for training and 20% for testing. The data preprocessing included the following steps: Removing punctuation, Lowercase, Stop-word removal, Tokenization, Stemming, Lemmatization, and TF-IDF (Term Frequency – Inverse Document Frequency) Feature Extraction. The classification algorithms used were Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Long Short-Term Memory (LSTM), which were trained and evaluated with accuracy, precision, recall, F1-score, and AUC-ROC. Experimental results indicated that SVM outperforms the other models with respect to accuracy (99.21%), precision (99.25%), recall (99.23%), F1-Score (99.24%) and AUC-ROC (99.96%). To make the classifications auditable, SHapley Additive exPlanations (SHAP) was applied uniformly to all five trained models rather than to the best model alone, permitting a direct comparison of the lexical evidence on which each classifier relies. The attributions converge: four of the five models rank the token “said” as the single most influential feature, and in every case, it shifts the prediction towards REAL, indicating that the models are detecting the attribution conventions of professional reporting rather than topic alone. The results show that the proposed NLP-ML-XAI framework is accurate, interpretable, and reliable for automatic fake news detection, which could be deployed by media organizations, fact checkers, and digital platforms to prevent spreading fake news online.

Keywords

Dataset, Fake News, Machine Learning, Prediction, Repository.

References

1. Hadeer Ahmed, Issa Traore, and Sherif Saad, “Detection of Online Fake News Using N-Gram Analysis and Machine Learning Techniques,” International Conference on Intelligent, Secure, and Dependable Systems in Distributed and Cloud Environments, pp. 127-138, 2017.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Nipa Akter et al., “Advanced Detection and Forecasting of Fake News on Social Media Platforms using Natural Language Processing and Artificial Intelligence,” Journal of Posthumanism, vol. 5, no. 6, pp. 3208-3236, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Jawaher Alghamdi, Yuqing Lin, and Suhuai Luo, “A Comparative Study of Machine Learning and Deep Learning a Techniques for Fake News Detection,” Information, vol. 13, no. 12, pp. 1-28, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Hunt Allcott, and Matthew Gentzkow, “Social Media and Fake News in the 2016 Election,” Journal of Economic Perspectives, vol. 31, no. 2, pp. 211-236, 2017.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Emad Alsuwat, and Hatim Alsuwat, “An Improved Multi-Modal Framework for Fake News Detection using NLP and Bi-LSTM,” The Journal of Supercomputing, vol. 81, no. 1, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Isabel Bezzaoui et al., “Explainable AI for Online Disinformation Detection: Insights from a Design Science Research Project,” Electronic Markets, vol. 35, no. 1, pp. 1-28, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Steven Bird, Ewan Klein, and Edward Loper, Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit, O’Reilly Media, 2009.
   [Google Scholar]
8. Jawaher Alghamdi, Suhuai Luo, and Yuqing Lin, “A Comprehensive Survey on Machine Learning Approaches for Fake News Detection,” Multimedia Tools and Applications, vol. 83, pp. 51009-51067, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Vaishali U. Gongane, Mousami V. Munot, and Alwin D. Anuse, “A Survey of Explainable AI Techniques for Detection of Fake News and Hate Speech on Social Media Platforms,” Journal of Computational Social Science, vol. 7, no. 1, pp. 587-623, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Haewoon Kwak et al., “What is Twitter, a Social Network or a News Media?,” Proceedings of the 19^th International Conference on World Wide Web, Daejeon, Korea, pp. 591-600, 2010.
    [CrossRef] [Google Scholar] [Publisher Link]
11. David M.J. Lazer et al., “The Science of Fake News,” Science, vol. 359, no. 6380, pp. 1094-1096, 2018.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Pooja Malhotra, and S.K. Malik, “Fake News Detection using Ensemble Techniques,” Multimedia Tools and Applications, vol. 83, no. 14, pp. 42037-42062, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Silvi Munawaroh, “Explainable AI (XAI) for Fake News Detection: A Review of Interpretability in Deep Learning Models for Misinformation Classification,” International Journal of Research and Applied Technology, vol. 4, no. 2, pp. 334-340, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. K. Neela, K. Deekshitha, and R. Deepa, “An Ensemble Learning, Frame Work for Robust Fake News Detection,” International Journal of Engineering Research and Technology, vol. 13, no. 1, pp. 1-6, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Halyna Padalko et al., “Ensemble Machine Learning Approaches for Fake News Classification,” Radioelectronic and Computer Systems, no. 4, pp. 5-19, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Badugu Akshitha Priya et al., “Fake News Detection using Natural Language Processing,” International Journal of Computer Technology and Electronics Communication, vol. 9, no. 2, pp. 541-550, 2026.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Hannah Rashkin et al., “Truth of Varying Shades: Analyzing Language in Fake News and Political Fact-Checking,” Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, pp. 2931-2937, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Saurabh Pratap Singh Rathore et al., “Comparative Analysis of Machine Learning Models for Fake News Detection using a Natural Language Processing,” 2024 1^st International Conference on Advances in Computing, Communication and Networking, Greater Noida, India, pp. 1389-1393, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Kai Shu et al., “Fake News Detection on Social Media: A Data Mining Perspective,” ACM SIGKDD Explorations Newsletter, vol. 19, no. 1, pp. 22-36, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
20. William Yang Wang, ““Liar, Liar Pants on Fire”: A New Benchmark Dataset for Fake News Detection,” Proceedings of the 55^th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, pp. 422-426, 2017.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Jawaher Alghamdi, Yuqing Lin, and Suhuai Luo, “Cross-Domain Fake News Detection using a Prompt-Based Approach,” Future Internet, vol. 16, no. 8, pp. 1-16, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Xinyi Zhou, and Reza Zafarani, “A Survey of Fake News: Fundamental Theories, Detection Methods, and Opportunities,” ACM Computing Surveys, vol. 53, no. 5, pp. 1-40, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]