Monzer

Fake News Detection

Developed a high-accuracy fake news detection system using Ensemble and SVM methods. Collected and preprocessed large datasets from various sources with NLTK and Pandas. Applied TF-IDF and CountVectorizer for feature extraction, converting text into numerical data for model training. Leveraged PyTorch and scikit-learn for building, training, and evaluating the models, achieving an accuracy of 98.70% with Random Forest and 98.47% with SVM. The model maintained precision, recall, and F1-scores above 98%.

• Python,
• PyTorch,
• scikitLearn,
• Pandas