Title: A recommender framework for the evaluation of end user experience in adaptive technology enhanced learning

Authors: Catherine Mulwa; Seamus Lawless; Ian O'Keeffe; Mary Sharp; Vincent Wade

Addresses: Centre for Next Generation Localisation, Knowledge and Data Engineering Group, School of Computer Science and Statistics, Trinity College, Dublin, Ireland. ' Centre for Next Generation Localisation, Knowledge and Data Engineering Group, School of Computer Science and Statistics, Trinity College, Dublin, Ireland. ' Centre for Next Generation Localisation, Knowledge and Data Engineering Group, School of Computer Science and Statistics, Trinity College, Dublin, Ireland. ' Centre for Next Generation Localisation, Knowledge and Data Engineering Group, School of Computer Science and Statistics, Trinity College, Dublin, Ireland. ' Centre for Next Generation Localisation, Knowledge and Data Engineering Group, School of Computer Science and Statistics, Trinity College, Dublin, Ireland

Abstract: Adaptive Technology Enhanced Learning (TEL) has attracted significant interest with the promise of supporting individual learning tailored to the unique circumstances, preferences and prior knowledge of a learner. However, the evaluation of the overall performance of such systems is a major challenge, as the adaptive TEL system reacts differently for each individual user and context of use. Evaluation of such systems is significant but very complex area of research in itself since depending on the aspect of personalisation that needs to be evaluated. Several evaluation techniques need to be combined and executed differently. This paper proposed a novel recommender framework built upon an evaluation educational data set using a hybrid recommend approach to identify appropriate procedures. Recommendations are to software developers and users of adaptive TEL systems. A review and analyses of evaluation studies on adaptive TEL systems was conducted. Based on the analysed results, an educational evaluation data set was created.

Keywords: education evaluation; evaluation data sets; personalised learning; recommender frameworks; evaluation frameworks; end users; user experiences; individual learning; unique circumstances; unique preferences; prior knowledge; learners; overall performance; system evaluation; personalisation; evaluation techniques; educational data sets; hybrid recommend approaches; software developers; internet; world wide web; Ireland; adaptive technology enhanced learning; dataTEL; data-supported learning; R&D; research and development.

DOI: 10.1504/IJTEL.2012.048312

International Journal of Technology Enhanced Learning, 2012 Vol.4 No.1/2, pp.67 - 84

Received: 30 Apr 2012
Accepted: 17 May 2012

Published online: 31 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article