Prediction of Stock Values using Sentiment Analysis on Twitter Data

Today, public opinion on social media is used as a primary key source to take informed decisions like to buy a product, to invest in a stock a company or to predict whether a movie would be block buster at the box office and so on. Manual digestion of such a huge data is very tedious and time consuming. Sentiment analysis is a technique which can be used to categorize emotions/feelings within peoples opinions expressed within an online mention. , automatically without manual intervention. Among all the applications of the sentiment analysis, the stock value prediction is quiet a difficult task since it is dependent on the demand of the stock and new information significantly. Also, it has been an active area of research for a long time. In our experiment we show how to connect to twitter and perform sentiment analysis. We used TextBlob method to build the prediction model. The main objective of this study is to determine the accuracy of a machine learning technique (TextBlob) with respect to providing a positive, negative and a neutral classification using Sentiment Analysis for stock related tweets. Our experiment shows that the percentage for positive sentiment of tweets are significantly higher