Abstract?The spread of fake news or hoaxes in this digital era, especially regarding issues related to Artificial Intelligence (AI) and technology,is becoming increasingly concerning, as it can trigger public misunderstanding and decrease trust in technological advancements. News such as claims that AI will lead to mass unemployment is a clear example of the spread of misleading information. Therefore, a system capable of accurately detecting fake news is needed. The aim of this study is to develop a fake news detection system that can accurately identify hoaxes related to AI and Technology. This research proposes a hybrid deep learning method that combines Convolutional Neural Network (CNN) and Support Vector Machine (SVM) to improve the accuracy of hoax news detection. CNN is used to extract complex features from news texts, while SVM is employed as the classifier due to its strength in separating classes with optimal margins. The selection of this method is based on previous studies that indicate each approach has good performance, yet specific limitations. By combining the two, it is expected to achieve more optimal results in detecting fake news, particularly on AI and technology topics. The evaluation was conducted using a dataset of news articles related to AI and technology, which had undergone preprocessing, feature extraction using TF-IDF, and feature expansion with GloVe embedding. The results showed that the CNN–SVM hybrid model outperformed the individual methods in terms of accuracy.