Using Controlled Vocabularies in Automated Subject Classification of Textual Web Pages, in the Context of Browsing

Automated subject classification has been a challenging research issue for several decades now. The purpose of this thesis is to determine to what degree controlled vocabularies that have been traditionally used in libraries could be utilised in automated classification of textual Web pages, in the context of browsing. Usefulness of different characteristics of controlled vocabularies for automated classification is explored, such as captions of classes from classification systems and terms from thesauri and/or subject heading systems. The classification algorithm would be developed based on a research article collection, and tested on Web pages.