Framework of kit-build concept map for automatic diagnosis and its preliminary use

In this paper, we propose a framework of Kit-Build Concept Map (we call it as KB map) where a concept map made by a learner can be diagnosed automatically. In this research, we have divided the task to make a concept map into two sub-tasks: (1) "segmentation task" where parts of the concept map (nodes and links) are extracted from learning resources and (2) "structuring task" where the extracted parts are integrated into a map. In the framework of kit-build concept map, a learner is given a set of parts of a concept map and then re-builds the concept map by combining the given parts. In this process, the segmentation task becomes a task of recognition of the given parts and the structuring task remains as it is. The concept map should be prepared beforehand by a teacher or domain expert. We call this map "goal map." The necessary and sufficient parts (kit) are generated by decomposing the goal map. The parts are provided to learners, and then the learners are required to build concept maps (learner maps) by connecting the parts. Since the same parts are used both in the goal map and a learner map, it is possible to find defects in the learner map as the differences from the goal map. By overlaying several learners' maps, then, a group map can be generated. By comparing the group map with the goal map, differences between the goal map and the group of the learners are detected. We have also realized procedure to re-examine the goal map based on the differences between the group map and the goal map. We have already developed a system that realized the framework of the KB map. Through a preliminary use of the system, we have confirmed that the system works along with the framework of KB map. Evaluation of learning effect is our future work.