Apport des ontologies pour le calcul de la similarit\'e s\'emantique au sein d'un syst\`eme de recommandation

TL;DR

This paper explores how ontologies can be used to compute semantic similarity in recommender systems, enhancing the understanding of textual data for better recommendations.

Contribution

It proposes a novel approach for calculating ontology-based semantic similarity specifically tailored for recommender systems.

Findings

Demonstrates the effectiveness of ontology-based similarity measures

Improves recommendation accuracy through semantic analysis

Integrates ontology methods with existing similarity calculations

Abstract

Measurement of the semantic relatedness or likeness between terms, words, or text data plays an important role in different applications dealing with textual data such as knowledge acquisition, recommender system, and natural language processing. Over the past few years, many ontologies have been developed and used as a form of structured representation of knowledge bases for information systems. The calculation of semantic similarity from ontology has developed and depending on the context is complemented by other similarity calculation methods. In this paper, we propose and carry on an approach for the calculation of ontology-based semantic similarity using in the context of a recommender system.