This paper aims to predict whether a given news article is real or fake. We use the dataset available on Kaggle. We then implement several deep learning models (Long short-term Memory (LSTM), Multi-layerPerceptron (MLP), Convolution Neural Networks (CNN), Hybrid CNN-LSTM on this dataset. For these models we examine the effects of character-based vs. word-based models and pretrained embeddings vs. learned embeddings. We also compare the accuracies of various models and report the best accuracy which we would get from a particular model.