A Markov-based Recommendation Model for Exploring the Transfer of Learning on the Web.

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. [ABSTRACT FROM AUTHOR]

Copyright of Educational Technology & Society is the property of International Forum of Educational Technology & Society (IFETS) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)