A Comparative Study of Machine Learning Algorithms for Classifying Real and Fake COVID-19 Tweets

Khan, Muhammad Hunzla Naqi (2025) A Comparative Study of Machine Learning Algorithms for Classifying Real and Fake COVID-19 Tweets. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (945kB) | Preview
Preview	PDF (Configuration Manual) Download (952kB) | Preview

Abstract

The fast-growing amount of web content led to the spreading demand for automated systems that can tell true from fake facts. This study uses machine learning methods to categorize 6,420 COVID-19-associated tweets collected from publicly available dataset "COVID Fake News Dataset" on Kaggle. The dataset has real and fake label, it can be used for supervised learning. A Full NLP pipeline was applied, including text cleaning, TF-IDF vectorization and classification with 10 Supervised models: Logistic Regression, Decision Tree, Random Forest Gradient Boosting, AdaBoost, Passive Aggressive Classifier, Multinomial Naïve Bayes, K-Nearest Neighbors, XGBoost and Linear SVM. The evaluation was conducted by accuracy, precision, recall and F1-score.

Linear SVM was the best in terms of accuracy (92.29%), followed by Passive Aggressive (91.90%) and Logistic Regression (91.19%). Models such as AdaBoost and XGBoost underperformed due to sparsity and high dimensionality of TF-IDF features. The experimental results verify that traditional linear classifiers are still very powerful on short-text classification. The study provides evidence that classical supervised ML techniques are applicable to the fake text content detection problem and presents a benchmark platform which might be beneficial for future work. Recommendations include deep learning, dataset size and contextual embeddings.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Horn, Christian UNSPECIFIED
Subjects:	P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing R Medicine > Diseases > Outbreaks of disease > Epidemics > COVID-19 Pandemic, 2020- Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	07 Sep 2026 13:39
Last Modified:	07 Sep 2026 13:39
URI:	https://norma.ncirl.ie/id/eprint/9870

Actions (login required)

View Item