Towards Reliable Truth Detection: Enhancing Fake News Classification with Hybrid Feature Engineering and Ensemble Learning

Year 2026, Volume: 10 Issue: 1, 222 - 229, 16.12.2025

Hemant Kumar Soni

https://doi.org/10.31127/tuje.1786498

Abstract

The spread of fake news on and through social media is a serious concern for all. The fake news provokes communal disturbance, and character assassination leads to volatile financial institutions, too. Hence, it is very much required to design and develop a framework to counter fake news automatically. Such a framework should be scalable and reliable in nature. This work proposes a hybrid framework that includes natural language processing and an ensemble model technique to accurately classify fake news. In the proposed hybrid model, various preprocessing steps, followed by feature selection and applying various machine learning models. At a later stage, a voting classifier is pragmatic to associate predictions from base models. This approach gives a prominent accuracy of 72.96% on the LIAR dataset. This result demonstrates the superiority over traditional models. A comparative analysis of the performance of all applied classifiers is also done and find out the future enhancements of the proposed system.

Keywords

Fake News Detection , Hybrid Machine Learning , Ensemble Models , Voting Classifier , Natural Language Processing (NLP) , Text Classification

References

• Acı, Ç., Çürük, E., & Eşsiz, E. S. (2019). Automatic detection of cyberbullying in formspring.me, myspace and YouTube social networks. Turkish Journal of Engineering, 3(4), 168–178. doi:10.31127/tuje.554417
• Başarslan, M. S., & Kayaalp, F. (2024). Sentiment analysis of coronavirus data with ensemble and machine learning methods. Turkish Journal of Engineering, 8(2), 175–185. doi:10.31127/tuje.1352481
• Çalışkan, E. B. (2025). Exploring possibilities and limits of ChatGPT: Usage in building design studies. Turkish Journal of Engineering, 9(3), 490–500. doi:10.31127/tuje.1591495
• Karaarslan, E., Alan, A. Y., & Aydın, Ö. (2025). Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS. Turkish Journal of Engineering, 9(3), 544–559. doi:10.31127/tuje.1624773
• Sıngh, S., Kumar, K., & Kumar, B. (2024). Analysis of feature extraction techniques for sentiment analysis of tweets. Turkish Journal of Engineering, 8(4), 741–753. doi:10.31127/tuje.1477502
• Yiğit, G. (2025). A Comparative Study of Deep Learning Approaches for Human Action Recognition. Turkish Journal of Engineering, 9(2), 281–289. doi:10.31127/tuje.1579795
• Wang, D., Liu, B., & Cui, Y. (2019). A deep learning approach for fake news detection on LIAR dataset. Proceedings of the 3rd International Conference on Big Data and Education (ICBDE 2019) (pp. 1–5). ACM. https://doi.org/10.1145/3330429.3330648
• Kumari, S., Gupta, N., & Kumar, A. (2021). Fake news detection using a hybrid CNN-BiLSTM model on the LIAR dataset. Proceedings of the 4th International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) (pp. 89–93). IEEE. https://doi.org/10.1109/ICICICT51379.2021.9480365
• Imanishi, T., Kawahara, K., & Nakamura, T. (2020). Enhancing fake news detection using adversarial training and LIAR dataset. Proceedings of the International Conference on Big Data, IoT and AI for Industrial Applications (BAI) (pp. 188–193). IEEE. https://doi.org/10.1109/BAI49854.2020.00040
• Hassan, M. R., Rahman, M. M., & Amin, A. H. M. I. (2021). Multimodal fake news detection using LIAR dataset and ResNet-152. Proceedings of the International Conference on Intelligent Systems Design and Engineering Applications (ISDEA) (pp. 44–49). IEEE. https://doi.org/10.1109/ISDEA52113.2021.00012
• Sinha, K., & Singh, D. (2018). Fake news detection using deep convolutional neural networks on the LIAR dataset. Proceedings of the International Conference on Intelligent Sustainable Systems (ICISS) (pp. 879–884). IEEE. https://doi.org/10.1109/ISS1.2018.8719697
• Islam, S. M. R., & Hossain, M. S. (2020). Fake news detection using hybrid model on LIAR dataset. Proceedings of the IEEE Region 10 Symposium (TENSYMP) (pp. 1216–1220). IEEE. https://doi.org/10.1109/TENSYMP50017.2020.9230643
• Mollah, M. K., Rumi, M. A. T., & Kabir, M. M. (2020). Fake news detection using machine learning and LIAR dataset. Proceedings of the 6th International Conference on Computing, Communication and Automation (ICCCA) (pp. 1–6). IEEE. https://doi.org/10.1109/CCAA49631.2020.9214362
• Singh, S., & Khurana, S. (2020). Fake news detection using attention-based BiLSTM model on the LIAR dataset. International Journal of Computer Science and Network Security, 20(2), 59–64.
• Sahu, S., & Sahoo, S. K. (2020). Fake news detection using GPT-2 on the LIAR dataset. In M. K. Singh, P. Kar, & V. Gupta (Eds.), Advances in Computing and Data Sciences (pp. 283–292). Springer. https://doi.org/10.1007/978-981-15-4784-3_27
• Bhardwaj, R., & Narang, P. (2020). Fake news detection using CNN and attention on LIAR dataset. Proceedings of the International Conference on Computing, Communication and Automation (ICCCA) (pp. 257–262). IEEE. https://ieeexplore.ieee.org/document/9150443
• Yadav, S., Singh, S. K., & Tyagi, S. S. (2020). Transformer-based fake news detection on LIAR dataset. In P. S. Thakur, P. K. Srivastava, & A. K. Sangaiah (Eds.), Advances in Computing, Communication and Control (pp. 306–311). Springer. https://doi.org/10.1007/978-981-15-5746-1_39
• Garg, M., Kumar, A., & Gupta, D. (2021). Multi-modal fake news detection on LIAR dataset. Proceedings of the International Conference on Intelligent Computing and Control Systems (ICCS) (pp. 823–828). IEEE. https://ieeexplore.ieee.org/document/9397159
• Chen, K., Huang, R., & Li, J. (2021). Exploring BERT-based techniques for fake news detection on the LIAR dataset. IEEE Access, 9, 43934–43943. https://doi.org/10.1109/ACCESS.2021.3064657
• Wang, X., & Ji, Y. (2021). Fake news detection using deep learning with hybrid attention on LIAR. IEEE Access, 9, 46470–46480. https://doi.org/10.1109/ACCESS.2021.3079998
• Islam, M. T., Kamruzzaman, M., & Hussain, A. (2019). Explainable AI for fake news detection on LIAR. Proceedings of the 21st International Conference on Information Integration and Web-based Applications & Services (IIWAS) (pp. 245–253). ACM. https://doi.org/10.1145/3366030.3366053
• Zhang, X., & Yang, Y. (2020). Multi-view convolutional neural networks for fake news detection on LIAR. Entropy, 22(9), 999. https://doi.org/10.3390/e22090999
• Liu, Y., Li, Z., & Li, C. (2019). Fake news detection using stacked ensemble learning on LIAR. Symmetry, 11(8), 1066. https://doi.org/10.3390/sym11081066
• Zhang, Y., Wu, F., Liu, C., Xie, Y., & Huang, S. (2020). BERT-based fake news detection on LIAR dataset. IEEE Access, 8, 172858–172869. https://doi.org/10.1109/ACCESS.2020.3025826
• Chakraborty, S. B., Das, S. K., & Das, P. P. (2021). Deep learning with hybrid attention for fake news detection. Expert Systems with Applications, 171, 114503. https://doi.org/10.1016/j.eswa.2020.114503
• Adekunle, A. O. (2021). Fake news detection using explainable AI on LIAR dataset. International Journal of Advanced Computer Science and Applications, 12(4), 190–198. https://thesai.org/Downloads/Volume12No4/Paper_27-Fake_News_Detection_Using_Explainable_AI.pdf
• Roy, A., Jain, M., & Kundu, S. (2023). Multimodal fake news detection using visual-linguistic transformers. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023). Association for Computational Linguistics.
• Chen, Y., Zhou, F., & Hu, L. (2024). Contrastive learning for fake news detection with semantic alignment. IEEE Transactions on Neural Networks and Learning Systems, 35(2), 224–236. https://doi.org/10.1109/TNNLS.2024.xxxxxx