The rise of false information in everyday access media venues like social media feeds, news blogs, and online newspapers has made it difficult to identify reliable news sources, necessitating the development of computer algorithms that can assess the authenticity of online content. We focus on the automatic detection of false information in internet news in this research. We make a two-fold contribution. First, we present two new datasets for the purpose of detecting fake news, each of which covers seven different news categories. We give many explanatory analyses on the identification of linguistic discrepancies in false news content, as well as a detailed description of the collecting, annotation, and validation procedure. Second, we run a series of learning experiments in order to develop reliable fake news detectors. Furthermore, we presented comparisons of the automatic and manual detection of fake news.