SAmgI: Automatic Metadata Generation v2.0 PROCEEDINGS
Michael Meire, Katholieke Universiteit Leuven, Belgium ; Xavier Ochoa, ESPOL Escuela Superior Politécnica del Litoral, Ecuador ; Erik Duval, Katholieke Universiteit Leuven, Belgium
EdMedia: World Conference on Educational Media and Technology, in Vancouver, Canada ISBN 978-1-880094-62-4 Publisher: Association for the Advancement of Computing in Education (AACE), Waynesville, NC
Manual creation of metadata is tedious, error-prone and doesn't scale. As the amount of learning content continues to grow, it becomes less and less feasible to describe all available content manually. Moreover, the metadata humans create are not perfect. Therefore, we need a change in approach, trying to automate this process as much as possible. In this paper, we provide an overview of our work from the last three years on how to achieve this automation. We also present a software design and implementation that has been evaluated in practice and that is being deployed at large scale. We detail the architectural design goals that made us evolve from a first approach to the current one.
Meire, M., Ochoa, X. & Duval, E. (2007). SAmgI: Automatic Metadata Generation v2.0. In C. Montgomerie & J. Seale (Eds.), Proceedings of ED-MEDIA 2007--World Conference on Educational Multimedia, Hypermedia & Telecommunications (pp. 1195-1204). Vancouver, Canada: Association for the Advancement of Computing in Education (AACE). Retrieved November 18, 2017 from https://www.learntechlib.org/p/25528/.
© 2007 AACE