Using Sentiment Analysis for Stock Exchange Prediction

Abstract

The economic growth is a consensus in any country. To grow economically, it is necessary to channel the revenues for investment. One way of raising is the capital market and the stock exchanges. In this context, predicting the behavior of shares in the stock exchange is not a simple task, as itinvolves variables not always known and can undergo various influences, from the collective emotion to high-profile news. Such volatility can represent considerable financial losses for investors. In order to anticipate such changes in the market, it has been proposed various mechanisms trying to predict the behavior of an asset in the stock market, based on previously existing information. Such mechanisms include statistical data only, without considering the collective feeling. This paper is going to use natural language processing algorithms (LPN) to determine the collective mood on assets and later with the help of the SVM algorithm to extract patterns in an attempt to predict the active behaviour.