In today’s digital age, most smartphone users prefer reading news on social media rather than directly from news websites, which are typically more reliable. This shift poses significant challenges in verifying the authenticity of news and articles published on platforms like Facebook, Twitter, and WhatsApp groups. The spread of misinformation and rumors can be particularly harmful to society, making it crucial to stop the dissemination of fake content, especially in developing countries like India. Addressing this issue, a study utilized 10 distinct machine learning (ML) and deep learning (DL) classifiers to categorize a fake content dataset. These classifiers were developed using four traditional methods for text feature extraction. Additionally, an optimization mechanism and a convolutional neural network (CNN) model were incorporated into the hybrid model. By employing a variety of classifiers, the researchers were able to enhance performance significantly. The hybrid model, which combined the strengths of different classifiers, achieved an impressive 95% accuracy. This high level of accuracy demonstrates the potential of data analytics techniques in effectively combating the spread of fake content, highlighting the importance of developing robust systems for content verification in today’s digital landscape.