You can view the full text of this article for free using the link below.

Title: Modelling second language learners for learning task recommendation

Authors: Haoran Xie; Di Zou; Tak-Lam Wong; Fu Lee Wang

Addresses: Department of Mathematics and Information Technology, The Education University of Hong Kong, Hong Kong ' Department of English Language Education, The Education University of Hong Kong, Hong Kong ' Department of Computing Studies and Information, Douglas College, Canada ' Office of the President, Caritas Institute of Higher Education, Hong Kong

Abstract: How to recommend appropriate and effective learning tasks based on the characteristics of a second language learner is a vital question in the field of second language acquisition. In this research, we investigate the issue by dividing it into two sub-questions: how to model the characteristics of language learners as different learners may have varied expertise on and subjective preferences of many topics; and how to select learning tasks according to the constructed learner model. Research on the second sub-question has been widely conducted in domains such as recommender systems, and we focus on the first sub-question in this study from the perspective of how to model the preferred learning contexts of a learner in a non-intrusive manner. We conducted an experiment among eighty-two students, and the results showed that our proposed framework outperformed other systems as it provides significantly more effective and enjoyable word learning experience.

Keywords: learner modelling; context familiarity; task recommendation; word learning; e-learning.

DOI: 10.1504/IJIL.2018.088779

International Journal of Innovation and Learning, 2018 Vol.23 No.1, pp.76 - 92

Available online: 11 Dec 2017 *

Full-text access for editors Access for subscribers Free access Comment on this article