With the enormous growth of social data in recent years, fake news detection has gained increasing research attention and has been widely explored in various languages. Arabic language nature imposes various challenges, such as the complicated morphological structure and the limited resources. Therefore, the current state-of-the-art methods for fake news detection remain to be enhanced, which inspired us to explore the application of the emerging deep-learning architecture to Arabic text classification. In this paper, we present an ensemble model that enhances the attention mechanism to detect fake news in Arabic sentences. An attention mechanism unit is incorporated to highlight the critical information from the contextual feature vectors. The context-related vectors generated by the attention mechanism layers are then concatenated and passed into a classifier to predict the final label. The experimental results show that the attention mechanism improves the model’s performance while yielding 99.8% in accuracy.