Fake News Detection Using Machine Learning: A Performance Comparison

The rise of misinformation through digital platforms has caused widespread public concern. Fake news influences public opinion and disrupts social trust. In this research, we present a machine learning-based approach to detect fake news articles using natural language processing techniques. We applied text preprocessing, feature extraction methods (Term Frequency - Inverse Document Frequency (TF-IDF) and Bag-of-Words (BoW)), and trained multiple classification algorithms, including Logistic Regression, Naive Bayes, Random Forest, and Support Vector Machine (SVM). Results show that the best-performing model (BoW + Random Forest) achieved an accuracy of 99.74 %. The approach provides a scalable, automated solution for mitigating the spread of misinformation online.