Abstract

A single predefined learning path may not be ideal when learners' backgrounds are diverse and unpredictable during the development stage of the courseware. Very often, learners would prefer different learning sequences according to their needs and past experience. Our research focuses on the discovery of effective learning paths. Frequent sequences are extracted from previous successful learners' logs and be used to build a learning flow model of which the relationships between content materials are formulated by the use of conditional probability. Our experiment shows that learner performance would improve when such recommendations are available. Also, it is found that recommendation in the form of learning flow or network is better than recommendation of any single learning object.

Citation

Tsoi, K.K. & Ng, V. (2007). Constructing a Guidance Network with Learning Navigation Patterns. In C. Montgomerie & J. Seale (Eds.), Proceedings of ED-MEDIA 2007--World Conference on Educational Multimedia, Hypermedia & Telecommunications (pp. 3795-3803). Vancouver, Canada: Association for the Advancement of Computing in Education (AACE). Retrieved August 7, 2024 from https://www.learntechlib.org/primary/p/25924/.

© 2007 Association for the Advancement of Computing in Education (AACE)

Keywords

• Developmental Stages
• Learning Objects