Fake news denotes false and misleading information. Its social impact is profound, as it can alter public perceptions, influence political dynamics, and cause harm to individuals or communities. Hence, there is a pressing need for robust techniques to detect and curb the spread of fake news. This study explores the use of convolutional neural network (CNN), a type of deep learning model, alongside traditional classifiers like support vector machines (SVMs) and decision tree (DT), for fake news detection. These methodologies effectively identify patterns and relationships within vast and complex datasets, crucial for tackling the challenge of misinformation detection.