Abstract
Fake news has become an industry on its own, where users paid to write fake news and create clickbait content to allure the audience. Apparently, the detection of fake news is a crucial problem and several studies have proposed machine-learning-based techniques to combat fake news. Existing surveys present the review of proposed solutions, while this survey presents several aspects that are required to be considered before designing an effective solution. To this aim, we provide a comprehensive overview of false news detection. The survey presents (1) a clarity to problem definition by explaining different types of false information (like fake news, rumor, clickbait, satire, and hoax) with real-life examples, (2) a list of actors involved in spreading false information, (3) actions taken by service providers, (4) a list of publicly available datasets for fake news in three different formats, i.e., texts, images, and videos, (5) a novel three-phase detection model based on the time of detection, (6) four different taxonomies to classify research based on new-fangled viewpoints in order to provide a succinct roadmap for future, and (7) key bibliometric indicators. In a nutshell, the survey focuses on three key aspects represented as the three T's: Typology of false information, Time of detection, and Taxonomies to classify research. Finally, by reviewing and summarizing several studies on fake news, we outline some potential research directions.