DIGITAL LIBRARY
USING LEARNING ANALYTICS AND LEARNING STYLES TO PERSONALISE CONTENT IN AN ADAPTIVE EDUCATIONAL SYSTEM
University of Ulster (UNITED KINGDOM)
About this paper:
Appears in: EDULEARN14 Proceedings
Publication year: 2014
Pages: 7064-7073
ISBN: 978-84-617-0557-3
ISSN: 2340-1117
Conference name: 6th International Conference on Education and New Learning Technologies
Dates: 7-9 July, 2014
Location: Barcelona, Spain
Abstract:
The efforts towards providing personalised e-learning is an increasing trend due to the fact that content provision is usually a one size fits all approach. Students have different learning styles, skills and needs which dictate the way in which they learn. This paper presents ongoing research on the authors’ adaptive educational system called iPal (Integrated Personalised Assessment in Learning). iPal is designed to be a more effective learning environment to satisfy the online delivery of practical Science, technology, Engineering and Maths (STEM) subjects, as a supplementary course tool in higher education. The iPal presentation layer consists of an integrated virtual and game based learning environment which delivers theoretical and practical content. This paper will illustrate the use of emerging approaches including the use of learning analytics and learning styles with iPal. The aim of this paper is to show how these approaches are effective enablers in the delivery of personalised content.

The focus of this paper is based on a two tiered approach using implicit approaches, learning analytics and explicit approaches, learning styles to personalise content in iPal. This is achieved by more accurately assessing a student’s learning style by using a dual learning style assessment. A novel approach which incorporates a primary learning style uses a traditional explicit learning style instrument. This 90 item Honey and Mumford Learning Style assessment is initially used to adapt content for new students. The secondary learning style, an implicit approach uses learning analytics extracted from the iPal student model. An intelligent rule based system ensures that the most appropriate theoretical and practical content is presented to the student by automatically searching for patterns in the data.

A qualitative and quantitative study is presented comprising of over 100 undergraduate Computing students. It can be concluded that the significance of this research is that it provides clear evidence for the successful use of iPal as a supplementary course tool in higher education. The full paper will provide further details.
Keywords:
Adaptive Educational System, Learning Analytics, Learning Styles, Content Personalisation, Integrated Personalised Assessment in Learning.