188/4 E-Commerce Group
Institute of Software Technology and Interactive Systems
Vienna University of Technology
Favoritenstrasse 9-11/188, A-1040 Vienna, Austria

Mining User Knowledge in Learning Networks

Authors: 
M. Hochmeister
Publisher: 
Riga Technical University
Proceedings: 
Local Proceedings of the 10th International Conference BIR2011
Pages: 
267 - 274
Year: 
2011
Type: 
Speech with proceedings
Hidden Keywords: 
Department Focus: 
Business Informatics
TU Focus: 
Information and Communication Technology
ISBN: 
ISBN: 978-9984-30-197-6
Abstract: 
Intelligent tutoring systems rely on learner models to recommend useful learning resources. Learner models suffer from incomplete and inaccurate information about learners. Learning networks are web-based platforms where people share knowledge and collaboratively solve problems, which triggers learning mechanisms. In this paper, we present an approach that calculates learnersĀ“ competence scores based on their contributions and social interactions in a learning network. This may result in more complete and accurate learner models, which allow more suitable recommendations of learning resources. For evaluation, we conducted an experiment with 14 master students at university. The results show that our approach tends to underestimate competences, while it calculates 54% of the scores accurately. Student feedback suggests using the approach to recommend future courses as well as forming student groups.
Abstract German: 
Intelligent tutoring systems rely on learner models to recommend useful learning resources. Learner models suffer from incomplete and inaccurate information about learners. Learning networks are web-based platforms where people share knowledge and collaboratively solve problems, which triggers learning mechanisms. In this paper, we present an approach that calculates learnersĀ“ competence scores based on their contributions and social interactions in a learning network. This may result in more complete and accurate learner models, which allow more suitable recommendations of learning resources. For evaluation, we conducted an experiment with 14 master students at university. The results show that our approach tends to underestimate competences, while it calculates 54% of the scores accurately. Student feedback suggests using the approach to recommend future courses as well as forming student groups.