Using a variety of prediction models, such as Logistic Regression, Naive Bayes, Decision Tree Classifier, Decision Tree Regression, and Random Forest Classifier, this project analyzes the identification of fake news. A large dataset called WELFake was used to improve the models' resilience and reduce overfitting with 72,134 news articles—35,028 classified as legitimate news and 37,106 as false news—was produced by combining four popular news datasets: Kaggle, McIntire, Reuters, and BuzzFeed Political.
Course: CSE 422 Artificial Intelligence Spring 2023