On creating a student model to assess effective exploratory behaviour in an open learning environment

• Main Author: Bunt, Andrea
• Format: Others
• Language: English
• Published: 2009
• Online Access: http://hdl.handle.net/2429/11648

Open learning environments give users a high degree of freedom and control to explore. This freedom and control is beneficial for some students, resulting in a deeper understanding of the material than they would gain through traditional means of instruction. For others, this type of environment is problematic, since for various reasons, these students are not able to explore effectively. One way to address this problem is to augment the environments with tailored support. To provide feedback tailored to the student's difficulties, the environment must have some way of monitoring and assessing her exploration. This thesis investigates the creation of a student model that assesses the effectiveness of the student's exploratory behaviour. Monitoring user behaviour in an open learning environment is difficult since there is typically little information available to the model to make its assessment. The model can view with which items the student experiments, but does not have direct access to the effects of those experiments on her understanding of the domain. As a result, how to model effective exploratory behaviour has not been extensively researched. The Student Model in this thesis has been implemented and evaluated in the context of the Adaptive Coach for Exploration (ACE). The model monitors the student's exploration of ACE's activities to generate an assessment of how effectively the learner is exploring. Using this assessment, ACE's Coach provides tailored feedback to guide the student's exploration process. To handle the large amount of uncertainty present in the modelling task, the Student Model is based on Bayesian Networks. The features of ACE's Student Model have been developed and refined using two evaluations of ACE with human subjects. The first evaluation was used to evaluate the effects of including tailored support in an open learning environment, and also provided insight into ways to improve the Student Model's preliminary design. The second evaluation tested those improvements. Results of the evaluations found that both the frequency with which students accessed the tailored feedback and the number of activities that they explored effectively (as determined by the Student Model) were positively correlated with learning. === Science, Faculty of === Computer Science, Department of === Graduate