Online dictionary learning techniques for financial news analysis

The investor’s sentiments can be defined an investor’s attitude and opinion towards investing in the stocks market. Investor sentiment has been traditionally regarded as a myth by classical financial theories and has received little attention by researchers prior to 1990. The standard argument was that in the highly competitive financial market, suboptimal trading behaviors, such as paying attention to sentiment signals, is unrelated to fundamental value. It has been proposed by the efficient market hypothesis (EMH) that markets are efficient in that opportunities for profit are discovered so quickly that they cease to be opportunities. The EMH effectively states that no system can continually beat the market because if that system were to become public, everyone would use it, thus negating any potential gain. From the literature, it is evident that the application of investor sentiment for evaluating market behavior is achieving broad acceptance. This paper studies the application of Soft Computing to Investor Sentiment, focusing on the dictionary learning approach. Soft computing methods and various sentiment indicators are employed to obtain sample predictions of future trends in stock market returns. This paper’s contribution is to expose the key areas where research is being undertaken, and to attempt to quantify the degree of success associated with the different research approaches.