INTELLIGENT NEWS VERACITY CLASSIFIER FOR COVID-19 MISINFORMATION

The Intelligent News Veracity Classifier for COVID-19 Misinformation presents an effective and practical solution to address the rapid spread of false and misleading information during global health crises. By leveraging Natural Language Processing techniques. and supervised machine learning approaches, the system successfully classifies COVID-19-related news articles into True, False, or Misleading categories with reliable performance. The integration of text preprocessing, TF-IDF feature extraction, SMOTE-based class balancing, and Logistic Regression ensures accurate and unbiased prediction results. The developed system not only focuses on misinformation detection. but also provides additional value through its web-based architecture. The platform enables real-time news verification, secure user authentication, and administrative management of hospital information and health tips. This dual functionality enhances both technological effectiveness and practical usability. By incorporating tools such as scikit-learn for model development and a Flask-based deployment framework, the system demonstrates scalability, efficiency, and ease of integration into real-world environments. Experimental results indicate satisfactory accuracy and macro F1-score performance, confirming the reliability. of the proposed model across multiple classification categories. The use of SMOTE to address class imbalance further improves fairness and reduces bias toward majority classes. Comprehensive testing procedures validate that the system operates securely, consistently, and efficiently under different conditions. Overall, this project contributes to combating digital misinformation by providing an automated, intelligent, and accessible news verification platform. It supports public health awareness, informed decision-making, and trust in credible information. sources. The system serves as a foundational step toward developing more advanced AI-driven fact-checking solutions capable of handling emerging misinformation challenges in future global crises.

[1] H. Alhakami, W. Alhakami, A. Baz, M. Faizan, M. W. Khan, and A. Agrawal, “Evaluating intelligent methods for detecting COVID-19 fake news on social media platforms,” Electronics, vol. 11, no. 15, p. 2417, Aug. 2022, doi: 10.3390/electronics11152417. [2] V. Rathinapriya and J. Kalaivani, “An intelligent feature selection-based fake news detection model for pandemic situation with optimal attention based multiscale densenet with long short-term memory layer,” Applied Soft Computing, vol. 176, p. 113158, May 2025, doi: 10.1016/j.asoc.2025.113158. [3] A. R. Sanaullah, A. Das, A. Das, M. A. Kabir, and K. Shu, “Applications of machine learning for COVID-19 misinformation: A systematic review,” Cognitive Computation, vol. 14, no. 6, pp. 1–22, 2022, doi: 10.1007/s12559-022-10032-0. [4] A. Ul Hussna, M. G. R. Alam, R. Islam, B. F. Alkhamees, M. M. Hassan, and M. Z. Uddin, “Dissecting the infodemic: An in-depth analysis of COVID-19 misinformation detection on X (formerly Twitter) utilizing machine learning and deep learning techniques,” Heliyon, vol. 10, no. 18, p. e37760, Sep. 2024, doi: 10.1016/j.heliyon.2024.e37760. [5] M. Nabeel and C. Große, “Classifying COVID-19 disinformation on Twitter using a convolutional neural network,” in Proceedings of the 8th International Conference on Information Systems Security and Privacy (ICISSP 2022), SCITEPRESS – Science and Technology Publications, 2022, pp. 264–272, doi: 10.5220/0010774800003120. [6] S. Malek, C. Griffin, R. D. Fraleigh, R. Lennon, V. Monga, and L. Shen, “Intervention in health misinformation using large language models for automated detection, thematic analysis, and inoculation: Case study on COVID-19,” Journal of Medical Internet Research, vol. 28, p. e75500, Jan. 2026, doi: 10.2196/75500. [7] X. Song, J. Petrak, Y. Jiang, I. Singh, D. Maynard, and K. Bontcheva, “Classification aware neural topic model for COVID-19 disinformation categorisation,” PLoS ONE, vol. 16, no. 2, p. e0247086, Feb. 2021, doi: 10.1371/journal.pone.0247086. [8] A. Peda Gopi, G. Sai Avanthi, M. Himani, M. Leela Swarna, and B. Achitha, "Fake News Detection on Social Media Using Block Chain," Journal of Emerging Technologies and Innovative Research (JETIR), vol. 11, no. 10, pp. 142-152, Oct. 2024. ISSN: 2349-5162. [9] D. A. Juraev, "Fake News Detection Using Natural Language Processing and Machine Learning," The Chitransh Academic & Research Journal, vol. 1, no. 4, pp. 275-299, Sept. 2025. ISSN: 3049-303X. DOI: 10.5281/zenodo.17239827. [10] D. A. Juraev, "Fake News Detection Using Natural Language Processing and Machine Learning," The Chitransh Academic & Research Journal, vol. 1, no. 4, pp. 275-299, Sept. 2025. ISSN: 3049-303X. DOI: 10.5281/zenodo.17239827.