Catégorisation automatique des textes avec des mesures de similarité sémantiques

Abstract

In this project, we dealt with a problem related to the text categorization domain, which involves associating each non-classified document with its category using a Set of previously classified documents. Our goal is to evaluate the use of semantic similarity measures and their impact on automatic classification of texts using the Wordnet lexical database. The implementation of our project is done using java language and Weka library.