Online courses assessment through measuring and archetyping of usage data

Abstract

Database files and additional log files of Learning Management Systems (LMSs) contain an enormous volume of data which usually remain unexploited. A new methodology is proposed in order to analyse these data both on the level of both the courses and the learners. Specifically, regression analysis is proposed as a first step in the methodology in order to explore how e-learning contents and characteristics of the course (such as a theory or lab course, a first- or second-year course, etc.) influence performance. Further investigation of each course, according to learners' usage, is achieved by archetypal analysis, which pinpoints the typical usage. The proposed methodology was successfully applied to LMS data from a Greek University. The results confirmed the validity of the approach and showed a relationship between the educational content which was provided and its usage by the learners.

Keywords:

• LMS usage
• regression
• measures
• archetypal analysis
• data mining techniques

Notes on contributors

Ioannis Kazanidis is currently working at the Kavala's Institute of Technology as an adjoined professor. He received the MSc degree in Computing from the Coventry University and the Ph.D. degree in Educational Technology and Adaptive Educational Systems at University of Macedonia. His main research interests lie in the area of adaptive systems, data mining methods and algorithms, computer-supported collaborative learning, virtual words in education. He has published 20 papers in international journals and book chapters, and more than 30 papers in proceedings of conferences.

Theodosios Theodosiou is currently working at the University of TEI of Kavala as an adjoined assistant professor. He obtained his Bachelor's degree in biology, and his Master's and Ph.D. degree is in bioinformatics. His research interests are in the field of data mining and specifically in the field of biological text mining and biostatistics. The last couple of years he also applied specific data analysis methods to the field of Learning Management Systems where he has a few publications. He had participated in several research projects funded mainly by the European Union. The projects involved bioinformatics and biostatistics and were mainly conducted at the Institute of Agrobiotechnology at CERTH in Thessaloniki and at the Department of Informatics at Aristotle University of Thessaloniki.

Ioannis Petasakis is currently working at the Kavala's Institute of Technology as an adjoined professor. He received Bachelor in mathematics and MSc in biostatistics. His main research interests are in the fields of environmental statistics and biostatistics.

Stavros Valsamidis received a five-year Electrical Engineering Diploma from Department of Electrical Engineering, University of Thessaloniki, Greece, an MSc in Computer Science from University of London, UK and his Ph.D. from the Department of Electrical and Computer Engineering, University of Thrace, Greece. He is an Applications Professor in the Department of Accountancy, TEI of Kavalas, Greece. His research interests are in the areas of database systems, data mining, data analysis and web applications assessment.