Automatic Classification of Digital Objects for Improved Metadata Quality of Electronic Theses and Dissertations in Institutional Repositories

Abstract

Higher education institutions typically employ Institutional Repositories (IRs) in order to curate and make available Electronic Theses and Dissertations (ETDs). While most of these IRs are implemented with self-archiving functionalities, self-archiving practices are still a challenge. This arguably leads to inconsistencies in the tagging of digital objects with descriptive metadata, potentially compromising searching and browsing of scholarly research output in IRs. This paper proposes an approach to automatically classify ETDs in IRs, using supervised machine learning techniques, by extracting features from the minimum possible input expected from document authors: the ETD manuscript. The experiment results demonstrate the feasibility of automatically classifying IR ETDs and, additionally, ensuring that repository digital objects are appropriately structured. Automatic classification of repository objects has the obvious benefit of improving the searching and browsing of content in IRs and further presents opportunities for the implementation of third-party tools and extensions that could potentially result in effective self-archiving strategies.