Student modelling has been an early research topic in Artificial Intelligence in Education; various techniques have been used to recognize and adapt to the student’s behaviour and knowledge. Currently, the major growth directions of research are in open student modelling, group modelling, and the modelling of affect, attitude, motivation and other aspects of the student beyond that of the student’s grasp of the content being learned.
Open Learner Modelling (OLM), i.e., a scrutable, inspectable, and/or modifiable student model has been shown to improve the involvement and motivation of students, and also to encourage reflection on the student’s own state of knowledge.
My contribution to the European FP6 project LeActiveMath was to precisely integrate an Open Learner Modelling approach into the web-based learning environment. Among the various tasks and scientific questions implied by such a collaborative project, I was particularly involved in three aspects of the project:
- the specification of an Extended Open Learner Model (xOLM), a multi-layered evidence-based model, based on a variant of Dempster-Shafer Theory (DST) and encompassing learners' abilities such as mathematical competency, affective and motivational factors, meta-cognition and misconceptions;
- the design of the OLM component that support learners in exploring judgements made by the system, in inspecting justifications for such judgements and in challenging them;
- the definition of various modes of visualisation of these evidence and argumentations, as well as the implementation of a dedicated user interface, to be deployed in the LeActiveMath system.
- Morales, R., Van Labeke, N., Brna, P., and Chan, M. E. (2008). Open Learner Modelling as the Keystone of the Next Generation of Adaptive Learning Environments. In Intelligent User Interfaces: Adaptation and Personalization Systems and Technologies, Mourlas, C., and P. Germanako, eds. IGI Global, Information Science Reference, pp. 288-312. [PDF]
- Van Labeke, N., Brna, P., and Morales, R. (2007). Opening up the Interpretation Process in an Open Learner Model. International Journal of Artificial Intelligence in Education 17(3), pp. 305-338. [PDF]
- Morales, R., Van Labeke, N., and Brna, P. (2006). A Contingency Analysis of LeActiveMath ’s Learner Model. In Proceedings of the 5th Mexican International Conference on Artificial Intelligence (MICAI'06 - Apizaco, Mexico). Springer, pp. 208-217. [PDF] [DOI]
- Morales, R., Van Labeke, N., and Brna, P. (2006). Approximate modelling of the multi-dimensional learner. In Proceedings of the 8th International Conference on Intelligent Tutoring Systems (ITS'06 - Jhongli, Taiwan). Springer-Verlag, pp. 555-564. [PDF] [DOI]
- Morales, R., Van Labeke, N., and Brna, P. (2006). Towards a Learner Modelling Engine for the Semantic Web. In Proceedings of the 4th International Workshop on Applications of Semantic Web Technologies for E-Learning (SW-EL @ AH'06 - Dublin, Ireland). [PDF]
- Van Labeke, N., Callaway, C., and Moore, J. (2006). Student Model Dialogue. FP6/LeActiveMath Deliverable, D32. [PDF]
- Brna, P., Van Labeke, N., Morales, R., and Gibson, I. (2005). Open Sudent Model. FP6/LeActiveMath Deliverable, D29. [PDF]
- Brna, P., Van Labeke, N., Morales, R., Pain, H., and Porayska-Pomsta, K. (2005). Integration of Student Model in LeActiveMath. FP6/LeActiveMath Deliverable, D31. [PDF]
- Brna, P., Van Labeke, N., Morales, R., Pain, H., Porayska-Pomsta, K., and Andres, E. (2005). Diagnostic Functionalities. FP6/LeActiveMath Deliverable, D30. [PDF]
- Brna, P., Van Labeke, N., Morales, R., Mavrikis, M., Pain, H., Porayska-Pomsta, K., and Andres, E. (2004). Student Model Speciﬁcation. FP6/LeActiveMath Deliverable, D10. [PDF]