Automated Ontology Building for News Text using Associative Word Properties

Abstract

It is known in the literature that ontology had been used extensively in machine learning for performance enhancement for text retrieval. It is also shown that robust ontology with detailed description of the domain knowledge will contribute to the accuracy in the retrieval. Nevertheless, we argue in some domain such as news text retrieval, building an ontology manually can be costly for a large-scale news repository and especially with the changes in content due to the dynamic events. In addition, maintenance can be a dauting task to keep up with new words that are associated with new events. This paper demonstrates the attempt to fully automate the development of an ontology for identifying the news domain and its subdomain. The ontology specification is defined based on the needs of the accuracy in retrieval. The mechanism of generating the ontology specification is defined and the results of the retrieval performance is discussed.