Adaptivity based on learning styles is considered by several adaptive systems, aiming at providing content that matches with the learning styles of students in order to make learning easier for them. However, for providing proper adaptivity, the learning styles of students have to be identified first. In most systems, learning style questionnaires are used for this issue, but such questionnaires have to deal with several problems, for example, some lack in validity and reliability. In this paper, we describe a model for profiling learners that is based on the answers to the Index of Learning Styles questionnaire, a commonly used instrument for detecting learning styles in traditional and online learning. The introduced model aims at overcomes the limitations of the questionnaire with respect to validity and reliability. . It uses Multiple Correspondence Analysis together with proximity measure to detect the most likely style for a learner. The results show that the model can be considered sufficiently reliable for detecting profiles, while less reliable for the active and reflective styles, and that the sensitivity of the proximity measure is an important issue and needs to be addressed. Additionally, an analysis of the profiles shows that some of them overlap because of their reciprocal influences. It can be concluded for the effectiveness of the approach for finding authentic profiles, even when unexpected relationships are found. Therefore, the model provides us with more accurate information about the learner by identifying the most influent learning style of a learner and its main characteristics.
[1]
D. Kolb.
Experiential Learning: Experience as the Source of Learning and Development
,
1983
.
[2]
A. Morineau,et al.
Multivariate descriptive statistical analysis
,
1984
.
[3]
R. Clarke,et al.
Theory and Applications of Correspondence Analysis
,
1985
.
[4]
R. Felder,et al.
Learning and Teaching Styles in Engineering Education.
,
1988
.
[5]
Hongchi Shi,et al.
An intelligent distributed environment for active learning
,
2001,
JERC.
[6]
Clara-Inés Peña,et al.
Intelligent Agents in a Teaching and Learning Environment on the Web
,
2002
.
[7]
Kyparisia A. Papanikolaou,et al.
An instructional framework supporting personalized learning on the Web
,
2003,
Proceedings 3rd IEEE International Conference on Advanced Technologies.
[8]
F. Coffield.
Should We Be Using Learning Styles? What Research Has to Say to Practice
,
2004
.
[9]
R. Felder,et al.
Applications, Reliability and Validity of the Index of Learning Styles*
,
2005
.
[10]
Dip. Ingegneria Informatica,et al.
Investigating relationships within the Index of Learning Styles : a data driven approach
,
2007
.