Autonomous filter engine based on knowledge acquisition from the Web

Abstract

For a long time filtering data has been a very important matter. With the growth of the Internet this question has become more and more pressing. Everyone knows that finding information is not always very easy, because of the large amount of data that the network contains. More generally, our concern here is not only to find what is interesting to download but also to avoid what is unsuitable. One of the different ways recently explored to address the question of filtering and rating information is to apply the studies done in the field of linguistic and artificial intelligence to the Web. In this context, we would like to show that it is possible to build an easy going and low cost tool to compare information. This tool will use automatically extracted and selected Web contents to build a specialized knowledge database that can easily be adapted to any subject in any language.