NLP-Based Fake News Detection Using Machine Learning and Transformer Models

This paper discussed the development of an NLP approach forfake news filtering which turned the misinformation screening task into a supervised article categorisation problem. The proposed system classified the data set, which contained 1,200 labeled instances (600 fake and 600 real) both in terms of text and credibility metadata. The study followed a research process of data preparation, text cleaning, feature extraction, training and validation, testing and metrics. This approach kept the experiment within well-controlled conditions; the experiment is not a product of the algorithm. The findings show a hierarchy. The base models were good starting points, especially support vector machine and random forest, but had sparse representations and lacked semantic modelling. The contextual embedding model boosted the accuracy by capturing semantics of sentences. We obtained the highest performance (94.24% accuracy, 93.48% precision, 94.51% recall, 93.99% F1-score) from our Hybrid Transformer-LightGBM model. It had a confusion matrix of correctly identified 94 real samples, correctly identified 86 fake samples, incorrectly identified 6 real samples, and fake samples not detected 5. This is acceptable for a research model, but not a final product for interactive use. This research also affirms a common misnomer: fake news detection is not fact-checking. A classifier can find cues on metadata and text that have been learned; it cannot verify disputed burden of proof, legal purpose and satire, dynamic context and intent. Future work needs to increase the size of the dataset of verified news articles, use specific (and code-mixed) languages, fact-checking feeds, explainable AI, images, screenshots and telecommunications tweets. A dashboard to show confidence, highlighted cues and verification would be the best addition. It offers a filter from data columns to metrics, too, needed when AI-determined results may be questioned by examiners or managers. Existing frameworks offer a basis for this.

[1]     Khanam, Z., Alwasel, B.N., Sirafi, H. and Rashid, M. (2021) ‘Fake news detection using machine learning approaches’, IOP Conference Series: Materials Science and Engineering, 1099(1), 012040. doi: 10.1088/1757-899X/1099/1/012040. [2]     Khan, J.Y., Khondaker, M.T.I., Afroz, S., Uddin, G. and Iqbal, A. (2021) ‘A benchmark study of machine learning models for online fake news detection’, Machine Learning with Applications, 4, 100032. doi: 10.1016/j.mlwa.2021.100032. [3]     Mridha, M.F., Keya, A.J., Hamid, M.A., Monowar, M.M. and Rahman, M.S. (2021) ‘A comprehensive review on fake news detection with deep learning’, IEEE Access, 9, pp. 156151–156170. doi: 10.1109/ACCESS.2021.3129329. [4]     Nasir, J.A., Khan, O.S. and Varlamis, I. (2021) ‘Fake news detection: A hybrid CNN-RNN based deep learning approach’, International Journal of Information Management Data Insights, 1(1), 100007. doi: 10.1016/j.jjimei.2020.100007. [5]     Samadi, M., Mousavian, M. and Momtazi, S. (2021) ‘Deep contextualized text representation and learning for fake news detection’, Information Processing & Management, 58(6), 102723. doi: 10.1016/j.ipm.2021.102723. [6]     Kula, S., Kozik, R., Choraś, M. and Woźniak, M. (2021) ‘Transformer based models in fake news detection’, in Paszynski, M. et al. (eds.) Computational Science – ICCS 2021. Cham: Springer, pp. 28–38. doi: 10.1007/978-3-030-77970-2_3. [7]     Saleh, H., Alharbi, A. and Alsamhi, S.H. (2021) ‘OPCNN-FAKE: Optimized convolutional neural network for fake news detection’, IEEE Access, 9, pp. 129471–129489. doi: 10.1109/ACCESS.2021.3112806. [8]     Jain, V., Kaliyar, R.K., Goswami, A., Narang, P. and Sharma, Y. (2022) ‘AENeT: An attention-enabled neural architecture for fake news detection using contextual features’, Neural Computing and Applications, 34(1), pp. 771–782. doi: 10.1007/s00521-021-06450-4. [9]     Raza, S. and Ding, C. (2022) ‘Fake news detection based on news content and social contexts: A transformer-based approach’, International Journal of Data Science and Analytics, 13(4), pp. 335–362. doi: 10.1007/s41060-021-00302-z. [10]   Seddari, N., Derhab, A., Belaoued, M., Halboob, W., Al-Muhtadi, J. and Bouras, A. (2022) ‘A hybrid linguistic and knowledge-based analysis approach for fake news detection on social media’, IEEE Access, 10, pp. 62097–62109. doi: 10.1109/ACCESS.2022.3181184. [11]   Rohera, D., Shethna, H., Patel, K., Thakker, U., Tanwar, S., Gupta, R., Hong, W.-C. and Sharma, R. (2022) ‘A taxonomy of fake news classification techniques: Survey and implementation aspects’, IEEE Access, 10, pp. 30367–30394. doi: 10.1109/ACCESS.2022.3159651. [12]   Gupta, A., Kumar, N., Prabhat, P., Gupta, R., Tanwar, S., Sharma, G., Bokoro, P.N. and Sharma, R. (2022) ‘Combating fake news: Stakeholder interventions and potential solutions’, IEEE Access, 10, pp. 78268–78289. doi: 10.1109/ACCESS.2022.3193670. [13]   Li, J. and Lei, M. (2022) ‘A brief survey for fake news detection via deep learning models’, Procedia Computer Science, 214, pp. 1339–1344. doi: 10.1016/j.procs.2022.11.314. [14]   Rai, N., Kumar, D., Kaushik, N., Raj, C. and Ali, A. (2022) ‘Fake news classification using transformer based enhanced LSTM and BERT’, International Journal of Cognitive Computing in Engineering, 3, pp. 98–105. doi: 10.1016/j.ijcce.2022.03.003. [15]   Segura-Bedmar, I. and Alonso-Bartolome, S. (2022) ‘Multimodal fake news detection’, Information, 13(6), 284. doi: 10.3390/info13060284. [16]   Aïmeur, E., Amri, S. and Brassard, G. (2023) ‘Fake news, disinformation and misinformation in social media: A review’, Social Network Analysis and Mining, 13, Article 30. doi: 10.1007/s13278-023-01028-5. [17]   Capuano, N., Fenza, G., Loia, V. and Nota, F.D. (2023) ‘Content-based fake news detection with machine and deep learning: A systematic review’, Neurocomputing, 530, pp. 91–103. doi: 10.1016/j.neucom.2023.02.005. [18]   Essa, E., Omar, K. and Alqahtani, A. (2023) ‘Fake news detection based on a hybrid BERT and LightGBM models’, Complex & Intelligent Systems, 9(6), pp. 6581–6592. doi: 10.1007/s40747-023-01098-0. [19]   Jing, J., Wu, H., Sun, J., Fang, X. and Zhang, H. (2023) ‘Multimodal fake news detection via progressive fusion networks’, Information Processing & Management, 60(1), 103120. doi: 10.1016/j.ipm.2022.103120. [20]   Alghamdi, J., Lin, Y. and Luo, S. (2023) ‘Towards COVID-19 fake news detection using transformer-based models’, Knowledge-Based Systems, 274, 110642. doi: 10.1016/j.knosys.2023.110642. [21]   Mohawesh, R., Maqsood, S. and Althebyan, Q. (2023) ‘Multilingual deep learning framework for fake news detection using capsule neural network’, Journal of Intelligent Information Systems, 60(3), pp. 655–671. doi: 10.1007/s10844-023-00788-y. [22]   Narayanan, M.B., Ramesh, A.K., Gayathri, K.S. and Shahina, A. (2023) ‘Fake news detection using a deep learning transformer based encoder-decoder architecture’, Journal of Intelligent & Fuzzy Systems, 45(5), pp. 8001–8013. doi: 10.3233/JIFS-223980. [23]   Truică, C.-O. and Apostol, E.-S. (2023) ‘It’s all in the embedding! Fake news detection using document embeddings’, Mathematics, 11(3), 508. doi: 10.3390/math11030508. [24]   Yadav, A., Gaba, S., Khan, H., Budhiraja, I., Singh, A. and Singh, K.K. (2024) ‘ETMA: Efficient transformer-based multilevel attention framework for multimodal fake news detection’, IEEE Transactions on Computational Social Systems, 11(4), pp. 5015–5027. doi: 10.1109/TCSS.2023.3255242. [25]   Farhangian, F., Cruz, R.M.O. and Cavalcanti, G.D.C. (2024) ‘Fake news detection: Taxonomy and comparative study’, Information Fusion, 103, 102140. doi: 10.1016/j.inffus.2023.102140. [26]   Fang, X., Wu, H., Jing, J., Meng, Y., Yu, B., Yu, H. and Zhang, H. (2024) ‘NSEP: Early fake news detection via news semantic environment perception’, Information Processing & Management, 61(2), 103594. doi: 10.1016/j.ipm.2023.103594. [27]   Hashmi, E., Yayilgan, S.Y., Yamin, M.M., Ali, S. and Abomhara, M. (2024) ‘Advancing fake news detection: Hybrid deep learning with FastText and explainable AI’, IEEE Access, 12, pp. 44462–44480. doi: 10.1109/ACCESS.2024.3381038. [28]   Al-Quayed, F., Javed, D., Jhanjhi, N.Z., Humayun, M. and Alnusairi, T.S. (2024) ‘A hybrid transformer-based model for optimizing fake news detection’, IEEE Access, 12, pp. 160822–160834. doi: 10.1109/ACCESS.2024.3476432. [29]   Hu, B., Mao, Z. and Zhang, Y. (2025) ‘An overview of fake news detection: From a new perspective’, Fundamental Research, 5(1), pp. 332–346. doi: 10.1016/j.fmre.2024.01.017. [30]   Raza, N., Abdulkadir, S.J., Abid, Y.A., Albouq, S.S., Alwadain, A., Rehman, A.U., Sumiea, E.H. and Farhan, M. (2025) ‘Enhancing fake news detection with transformer-based deep learning: A multidisciplinary approach’, PLOS ONE, 20(9), e0330954. doi: 10.1371/journal.pone.0330954.