Stock market prediction has been an area of interest for a few decades now and much recently, there has been a lot of new research in the field of neural networks and natural language processing (NLP), that has resulted in satisfactory results. Sentiment analysis is one such sub-field of NLP that has made possible the extraction of emotions expressed in a body of text. These sentiments have been shown to co-relate with the change in stock prices. Previously twitter has been used to show a positive co-relation between the positive and negative sentiments gathered from a collection of tweets, and directional stock movements. In this paper, I expand upon these findings as I develop multiple predictive models that incorporates these technologies to predict not only the directional changes in the stock market but also the stock prices. For this purpose I use New York Times article headlines for the top 5 IT corporations listed on the S&P 500 index (Google, Microsoft, Amazon, Facebook and Apple), and use word2vec for encoding these headlines into vectors. These vectors are fed into LSTM NN, along with momentum-based economic indicators to supplement the predictive model. This has resulted in a MAPE (Mean Absolute Percentage Error) score of 1.15% for the regression based model and 65% direction accuracy, hence, indicating a positive co-relation between stock prices and public sentiment