Classifying and quantifying certain phenomena effect

The goal of this paper is to create a hybrid system that will investigate possible stock market changes immediately after financial news article appear and how this information influences the stock market behavior in order to improve the profitability of a short or medium time period investment. We proposed a multi-agent system that uses text mining, information extraction, pattern recognition, sentiment analysis and a trust model. The system classifies and quantifies certain phenomena (financial news influence) in order to compute the effect of some properties and its size on the stock market and also checks if we can use turbulence to detect disasters. It also searches a correlation between the effect of news articles and the trader´s behavior on the market. In order to validate our model a prototype was developed.