Nowadays on the internet, lots of information is spread every second by the people. On social media, most of the users do not verify the information and propagate it. Manually identifying fake news is a very tremendous problem for all. So, the need for an automatic system that efficiently detects fake news. This paper estimated a model that intuitionally distinguishes fake news from a news article. A new feature set for machine learning classifier has been proposed. Within the experiment, the dataset used has a combination of two datasets that contain equal true news and fake news articles of politics. From text fields of the dataset extract linguistic/stylometric features, a bag of words TF and BOW TF-IDF vector, after that apply the various machine learning models including bagging and boosting methods to achieve the best accuracy.