A significant task facing machine learning and natural language processing is real-time recognition of fake news generated automatically. Social media platforms contribute to the spread of uncertain information, context in which people of different backgrounds all over the world interact. The purpose of this work is to demonstrate the significant role of artificial intelligence in the remarkable generation of the content (here, content with a low degree of trust). As a result of this survey, after identifying and analyzing main research trends in fake news detection, current opportunities are highlighted where specific recommendations could be exploited as solutions for users, especially, on social media. Moreover, the experiments show that fake news can be generated easily through various interventions into the true news. It is about the fact distortion, subject-object exchange and cause confounding. Also, this work highlights the power of generating news with suspicious content using different classifiers of fake like Fakebox and the highly publicized ChatGPT.