Fake news becomes a major concern in the era of social media, as it can spread rapidly and has significant impacts on individuals and society. Society and individuals are negatively influenced both politically and socially by the widespread increase of fake news either generated by humans or machines. In the era of social networks such as Facebook, X (twitter) and WhatsApp, the quick rotation of fake news makes it challenging to evaluate its reliability promptly. Therefore, automated fake news detection tools have become a crucial requirement. To address the aforementioned issues, two data mining classification techniques were used as Extreme Gradient Boosting and Decision Tree with some python features. This study is designed to use Decision Tree and Extreme Gradient Boosting methods to develop an effective approach for detecting and classifying news as real or fake to obtain a reliable model performance. These models are trained on a labeled dataset consisting of both real and fake news. The performance of the models was evaluated using standard evaluation metrics such as accuracy, precision, recall, and F1-score. The proposed approach achieved 100% accuracy in distinguishing between real and fake news. It revealed and highlighted the potential of utilizing data mining techniques to combat the spread of fake news and provide valuable insights for researchers and practitioners in the field of information confirmation/verification and media literacy. We hope to use a different dataset to test the proposed model.