Social media platforms have simplified sharing and consuming news articles as compared to traditional news organizations which have led to the proliferation of fake news. In this project, the content of the news article and the existence of echo chambers in the social network is taken into account for fake news detection. A tensor representing social context is formed by combining the news, user and community information. The proposed method has been tested on a real-world dataset: BuzzFeed. The proposed method outperforms existing fake news detection methods by employing deep learning on news content and social context based features