developed a comprehensive solution for fake news detection using both deep learning and traditional machine learning models. I began by preprocessing the dataset, which involved handling missing values, combining relevant text fields, and preparing the text for model training through tokenization and padding. I implemented an LSTM model to capture the temporal dependencies in the text, achieving a high accuracy of 98.37%. In addition to deep learning, I explored various traditional machine learning models like Random Forest, SVM, Naive Bayes, and Gradient Boosting to compare their effectiveness in detecting fake news. The Random Forest model achieved the highest accuracy among traditional models with 91.10%.