This paper addresses the critical issue of fake news detection related to COVID-19, a pandemic that began in Wuhan, China, in December 2019 and rapidly spread worldwide. The authors highlight the significant role of social media in the rapid dissemination of both accurate and false information, which can lead to incorrect decisions and further complications in managing the pandemic. They propose an effective Convolutional Neural Network (CNN)-based deep learning model using word embedding to detect fake news. The model's architecture is optimized using grid search for hyper-parameter tuning. The proposed CNN model outperforms other state-of-the-art machine learning algorithms, achieving a mean accuracy of 96.19%, a mean F1-score of 95%, and an area under the ROC curve (AUC) of 0.985. The study emphasizes the importance of automated methods to combat the spread of misinformation, especially in the era of big data and social media.This paper addresses the critical issue of fake news detection related to COVID-19, a pandemic that began in Wuhan, China, in December 2019 and rapidly spread worldwide. The authors highlight the significant role of social media in the rapid dissemination of both accurate and false information, which can lead to incorrect decisions and further complications in managing the pandemic. They propose an effective Convolutional Neural Network (CNN)-based deep learning model using word embedding to detect fake news. The model's architecture is optimized using grid search for hyper-parameter tuning. The proposed CNN model outperforms other state-of-the-art machine learning algorithms, achieving a mean accuracy of 96.19%, a mean F1-score of 95%, and an area under the ROC curve (AUC) of 0.985. The study emphasizes the importance of automated methods to combat the spread of misinformation, especially in the era of big data and social media.