Machine Learning

Fake vs. Real News Classification Using Machine Learning

The Fake vs. Real News Classification Using Machine Learning system is a comprehensive machine learning solution that automatically classifies news articles as either real or fake using supervised learning techniques. This project is ideal for B.Tech, MCA, CSE, and engineering students as their final year project. It uses advanced algorithms like K-Nearest Neighbors (KNN) and Linear Support Vector Machine (SVM) with TF-IDF feature extraction to achieve 92.47% accuracy.

The system leverages TF-IDF vectorization with 5,000 features and n-gram range (1,2) on news article titles to capture meaningful linguistic patterns. It provides interactive visualizations, feature importance analysis, model comparison, and real-time news classification to help combat misinformation and support fact-checking efforts.

• Binary News Classification
• Linear SVM (92.47% Accuracy)
• KNN (88.93% Accuracy)
• TF-IDF Feature Extraction
• Feature Importance Analysis
• Real-time News Prediction
• Model Performance Comparison
• Interactive Visualizations
• 5-Fold Cross-Validation
• Flask Web Application