Cognitive Filtering of Textual Information Agents Based Implementation

The study presented in this paper has multiple objectives. The first objective is to automate the information filtering process by taking into account the relative importance of information and resources needed for its treatment. The second one is to demonstrate the applicability and contribution of an agents based implementation to automatic information filtering. The third one is to show how learning can improve the effectiveness of filtering and that automatic learning is necessary in the design of automatic information filtering systems. We propose an open, dynamic and evolving solution that offers to the filtering process the opportunity to learn, exploit the learned knowledge and adapt itself to the application environment. We have adopted agents to improve the response time compared to a sequential algorithmic solution. To validate our filtering approach, we led a set of experiments to evaluate performances of the techniques and tools we have developed