TABLE OF CONTENTS Mining textual document and time series concurrently, such as predicting the movements of stock prices based on news articles, is definitely an emerging topic in data mining society nowadays. Previous research has already suggested that relationships between news articles and stock prices do exist. In this paper, we try to explore such an opportunity and propose a systematic framework for predicting the movement of stock trends by analyzing the influence of news articles. In particular, we investigate the immediate impacts of news articles onto the stock market based on the Efficient Markets Hypothesis (EMH). Several data mining and text mining techniques are used in a novel way. Extensive experiments using real-life data are conducted, and encouraging results are obtained.
Without a doubt, human behaviors are always influenced by the environment. One of the most significant impacts that affect our behaviors certainly comes from the mass media, or to be more specific, from the news articles. Several research from different fields has already developed some well-defined theories to support it [2] [3]. For the stock prices fluctuation, it is totally because of we, human beings, who perform the bidding and asking activities. As news will influence our decisions and our decisions will influence the stock market, news will, in turn, affect the stock market indirectly.
