FACTCHECK AI: SUPERVISED LEARNING APPROACH TO CLASSIFYING MISINFORMATION

Abstract

The rapid proliferation of online news and social media platforms has led to an unprecedented spread of misinformation, making the detection of fake news critical for public awareness and societal stability. This study presents FactCheck AI, a supervised learning framework leveraging Natural Language Processing (NLP) techniques to classify news articles based on in-article attribution and linguistic features. By analyzing textual content, source credibility, and attribution patterns, the system identifies inconsistencies and indicators of falsified information. Multiple supervised learning models, including Support Vector Machines (SVM), Random Forests, and Logistic Regression, are evaluated to determine optimal performance for fake news detection. Experimental results demonstrate that FactCheck AI achieves high classification accuracy, effectively distinguishing genuine news from misinformation while providing interpretable insights into attribution-based cues. The framework underscores the potential of NLP-driven supervised learning in enhancing news verification processes, supporting media literacy, and mitigating the spread of fake news