Stock Direction Prediction Using Sentiment Analysis of News Articles Nipun Jain, Mohit Motiani, and Preeti Kaur Computer Engineering, Netaji Subhas Institute of Technology, University of Delhi, India preeti@nsit.ac.in Abstract. It is widely acknowledged that stock price prediction is a job full of challenges due to the highly unpredictable existence of financial markets. Many market participants or analysts, however, attempt to predict stock prices using different mathematical, econometric, or even neural network models in order to make money or understand the nature of the equity market. In the past few years, a lot of models based on deep learning have been gaining popularity for predicting the volatility of the stock market prices. In this paper, the outcomes of many classical deep learning models such as LSTMs, GRUs, CNNs and their several common variants are contrasted with two distinct stock price prediction targets: absolute stock price and volatility. The aim of the comparative study is to find out which model is the best fit for stock market prediction. We also attempt to research the relationship between news and stock trends, be- lieving that news stories have an impact on the stock market by incorporating sentiment analysis into our model. Our methodology was to scrape news articles of a particular stock and use the corpus gathered to generate a sentiment score which is further used as an input to the model. Keywords: Neural Network, Sentiment Analysis, Stock Market, News Scrapings 1 Introduction A stock also referred to as equity, is a security representing the holding of a fraction of the company. This grants the shareholder the right to a share of the assets and earnings of the corporation equal to how much of the stock they own. The stock market refers to the set of stocks and trades in which shares in publicly listed companies are acquired, exchanged and released on a daily basis. A stock market prediction is an attempt to forecast the future trend of an individ- ual stock, a particular sector of the market, or the market as a whole. These forecasts generally use fundamental analysis of a company or economy, or technical analysis of charts, or a combination of the two. The prediction of stock prices is a popular and significant problem. We can gain insight into market behavior over time with a good model for stock prediction, identify- ing patterns that would otherwise not have been observed. Machine learning would be an effective way to solve this issue with the rising computing capacity of the computer.