Text Opinion Mining to Analyze News for Stock Market Prediction

This is a known fact that news and stock prices are closely related and news usually has a great influence on stock market investment. There have been many researches aimed at identifying that relationship or predicting stock market movements using news analysis. Recently, massive news tests, called unstructured big-data, have been used to predict stock price. In this paper, we introduce a method of mining text opinions to analyze Korean language news in order to predict rises and falls on the KOSPI (Korea Composite Stock Price Index). Our method consists of carrying out the NLP (Natural Language Processing) of news, describing its features, categorizing and extracting the sentiments and opinions expressed by the writers. The method then identifies the correlation between news and stock market fluctuations. In our experiment, we show that our method can be used to understand unstructured big-data, and we also reveal that news’ sentiment can be used in predicting stock price fluctuations, whether up or down. The algorithm extracted experiments can be used to make predictions about stock market movements .