Causal model progressions as a foundation for intelligent learning environments
Artificial Intelligence - Special issue on artificial intelligence and learning environments
Compositional modeling: finding the right model for the job
Artificial Intelligence - Special issue: Qualitative reasoning about physical systems II
Artificial Intelligence - Special issue: Qualitative reasoning about physical systems II
Building problem solvers
Automated model selection for simulation based on relevance reasoning
Artificial Intelligence
The Andes Physics Tutoring System: Lessons Learned
International Journal of Artificial Intelligence in Education
Proceedings of the 2005 conference on Artificial Intelligence in Education: Supporting Learning through Intelligent and Socially Informed Technology
| Hi-index | 0.00 |
In science education, in order to facilitate a student's conceptual understanding, it is important to sequence a set of microworlds (which means a system and its model limited from educational viewpoint) of various complexity adaptively to the context of learning. We previously proposed Graph of Microworlds (GMW), a framework for indexing a set of microworlds based on their models. With GMW, it is possible to adaptively select the microworld a student should learn next, and to assist him/her in transferring between microworlds. However, it isn't easy to describe GMW because, for model-based indexing, an author must have the expertise in the process of modeling. In this paper, we propose a method for semi-automating the description of GMW by introducing an automatic modeling mechanism: compositional modeling. Our method assists an author in generating a set of indexed microworlds and also in considering educational meanings of the relations between them. We present how to design such a function and also illustrate how it works. A preliminary test with a prototype system showed the effectiveness of our method.