You are hereThesis / User Performance Using an Ontology-Driven Information Retrieval (ONTOIR) System

User Performance Using an Ontology-Driven Information Retrieval (ONTOIR) System


By murray - Posted on 31 March 2006

Enhancing the representation and relationship of information through ontology is a promising alternative approach for knowledge organization. This improved knowledge organization is vital for collocation of information and effective and efficient searching. This study concerned the testing of user performance when searching an ontology-driven information retrieval (ONTOIR) system that shows explicit relationships among resources. The study explores the possibilities of improving user performance in searching for information. The goal was to examine whether or not ontology enhances user performance in terms of recall and search time. The experiment was conducted with 40 participants to evaluate and compare the differences in user performance (recall and search time) between an ontology-driven information retrieval system and a traditional, thesaurus-driven information retrieval system.

Better recall and shorter search time were found when conducting relationship-based queries in an ontology-driven information retrieval system as compared to a thesaurus-based system. . Further studies comparing user performance with a cluster-based search engine and an ontology-driven information retrieval system are needed.