User modelling in Exploratory Learning Environments

A case-based reasoning inspired approach was used for modelling learners' exploratory learning behaviour in an intelligent system for teaching mathematical generalisation in classroom for pupils of 11 to 14 years old.

The user model was further exploited to support learning related activities,
such as prioritising feedback and grouping for collaboration. For feedback prioritisation, a mechanism based on Multi-criteria Decision Making was developed and tested with the help of educational experts. The grouping for collaboration approach was inspired from Group Technology, a method from cellular manufacturing systems, and its testing showed it produces meaningful groups. Both the feedback prioritisation and the grouping for collaboration mechanisms propose solutions that are particularly relevant for ELEs by considering pertinent criteria for this type of learning.

To ensure optimal coverage of the knowledge base, the user modelling approach was enhanced with adaptive mechanisms for expanding the knowledge base, which was tested on real and simulated data. This approach ensures that learner diagnostic is possible when the initial knowledge base is small and/or new behaviours are encountered over time.

- development of a user model for exploratory learning, describing user strategies
- using the learner model to prioritise the aspects that feedback in the system should address first
- development of a grouping approach for collaborative activities by taking into account the user strategies
- development of an adaptive mechanism for expanding the knowledge base over time