An ontology based fully automatic document classification system using an existing semi-automatic system

Abstract

Automatic classification of documents has become an important research area due to the exponential growth of digital content and because manual or semi-automatic organization is not effective. On one hand, manual and semi-automatic classification is very painstaking and labor-intensive. On the other hand, misclassifications due to vagueness of the documents and classification schemes are inevitable in these two methods. Hence, the current study sought to shed a light on these issues. This research proposes an automated system that can completely classify a given text document by minimizing the vocabulary ambiguities. One of our previous studies has developed a semi-automatic system for document classification and here we propose to extend it furthermore to obtain a fully automatic document classification system.