Predicting stock movement using sentiment analysis of Twitter feed

Collecting data from social networking sites is a popular way of opinion mining. These opinions show the sentimental state of a large number of people. In this paper, we have shown how much we can predict stock movement from Twitter's tweets sentiment analysis. Our work is done on one year's (2016) data of tweets that contained ‘stock market’, ‘stocktwits’, ‘AAPL’ keywords. ‘AAPL’ related tweets were used to see if these tweets can predict the company's stock indices whereas ‘stock market’, ‘stocktwits’ related tweets for predicting the stock market movement of US. Since we are predicting the stock values, we used Boosted Regression Tree model for this purpose.