Abstract: The rapid proliferation of fake news on digital platforms poses a significant challenge to public trust, social stability, and informed decision-making. To address this concern, this study investigates the effectiveness of conventional machine learning classifiers for fake news detection using hand-crafted textual features. Several widely used models, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression, and Random Forest, were evaluated after applying rigorous preprocessing and feature extraction techniques. Experimental results highlight that KNN and SVM demonstrated superior performance, achieving up to 88% accuracy in distinguishing between authentic and fabricated news. The findings underscore the importance of leveraging well-structured datasets and robust classification techniques to combat misinformation effectively. This work provides a foundation for developing scalable and reliable automated systems for mitigating the spread of misleading content in online environments.
Keywords: Fake News Detection, Machine Learning Classifiers, Fake News Dataset, Classifier Performance.
Downloads:
|
DOI:
10.17148/IJARCCE.2025.14826
[1] Aanchal Mishra, Rajnish Pandey, Awadhesh Maurya, Rajesh Kumar Singh, "Investigating Conventional Machine Learning Classifiers for Fake News Detection," International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), DOI: 10.17148/IJARCCE.2025.14826
