The paper presents a deep learning model based on Convolutional Neural Networks (CNN) for detecting fake news related to COVID-19. The model uses word embeddings to capture the meaning of text. To select the best CNN architecture, the authors used grid search to find optimal hyperparameters. They also compared their CNN model with various state-of-the-art machine learning algorithms for fake news detection. The CNN model achieved a mean accuracy of 96.19%, a mean F1-score of 95%, and an area under the ROC curve (AUC) of 0.985, outperforming other models. The spread of false information about COVID-19 has been labeled an "infodemic" by the World Health Organization (WHO), causing serious difficulties for governments trying to control the pandemic. The rapid spread of fake news, especially during the 2016 US elections, has shown the need for effective detection methods. Fake news is often presented in a way that makes people believe it is authentic. With the increasing number of platforms and the use of AI bots, the problem of fake news has become more severe. Manual detection is time-consuming and not feasible in the era of big data. The paper emphasizes the importance of using data science and machine learning techniques to detect fake news and make informed decisions. The integration of various techniques, technologies, and tools has made data science a crucial part of decision-making in the real world, especially with the rise of the Internet of Things (IoT).The paper presents a deep learning model based on Convolutional Neural Networks (CNN) for detecting fake news related to COVID-19. The model uses word embeddings to capture the meaning of text. To select the best CNN architecture, the authors used grid search to find optimal hyperparameters. They also compared their CNN model with various state-of-the-art machine learning algorithms for fake news detection. The CNN model achieved a mean accuracy of 96.19%, a mean F1-score of 95%, and an area under the ROC curve (AUC) of 0.985, outperforming other models. The spread of false information about COVID-19 has been labeled an "infodemic" by the World Health Organization (WHO), causing serious difficulties for governments trying to control the pandemic. The rapid spread of fake news, especially during the 2016 US elections, has shown the need for effective detection methods. Fake news is often presented in a way that makes people believe it is authentic. With the increasing number of platforms and the use of AI bots, the problem of fake news has become more severe. Manual detection is time-consuming and not feasible in the era of big data. The paper emphasizes the importance of using data science and machine learning techniques to detect fake news and make informed decisions. The integration of various techniques, technologies, and tools has made data science a crucial part of decision-making in the real world, especially with the rise of the Internet of Things (IoT).