文章基本信息

标题：A Markov-based Recommendation Model for Exploring the Transfer of Learning on the Web
本地全文：下载
作者：Yueh-Min Huang ; Tien-Chi Huang ; Kun-Te Wang 等
期刊名称：Educational Technology and Society
印刷版ISSN：1176-3647
电子版ISSN：1436-4522
出版年度：2009
卷号：12
期号：02
页码：144-144–162
出版社：IFETS - Attn Kinshuck
摘要：The ability to apply existing knowledge in new situations and settings is clearly a vital skill that all students need to develop. Nowhere is this truer than in the rapidly developing world of Web-based learning, which is characterized by non-sequential courses and the absence of an effective cross-subject guidance system. As a result, questions have arisen about how to best explore and stimulate the transfer of learning from one subject to another in electronically mediated courses of study. In this study, we argue that online learners would benefit from guidance along applicable group-learning paths. This paper proposes use of the learning sequence recommendation system (LSRS) to help learners achieve effective Web-based learning transfer using recommendations based on group-learning paths. We begin with a Markov chain model, which is a probability transition model, to accumulate transition probabilities among learning objects in a course of study. We further employ an entropy-based approach to assist this model in discovering one or more recommended learning paths through the course material. Statistical results showed that the proposed approach can provide students with dependable paths leading to higher achievement levels, both in terms of knowledge acquisition and integration, than those typically attained in more traditional learning environments. Our study also identified benefits for teachers, providing them with ideas and tools needed to design better online courses. Thus, our study points the way to a Web-based learning transfer model that enables teachers to refine the quality of their instruction and equips students with the tools to enhance the breadth and depth of their education.
关键词：Groups-learning paths, Transfer of learning, Markov chain model, Individual learning, Entropy