Affiliations: Department of Systems and Social Informatics, Graduate School of Information Science, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, 464-8603, Japan | [x] Department of Systems and Social Informatics, Graduate School of Information Science, Nagoya University. Furo-cho, Chikusa-ku, Nagoya 464-8603, Japan | [y] School of Electrical and Information Engineering, University of South Australia, Mawson Lakes Campus, South Australia 5095, Australia
Abstract: The discussion record in collaborative learning where participants generate their own answers by exchanging their opinions through a discussion is useful for other learners who tackle the same exercise. We propose a method for organizing solution knowledge in collaborative learning records as a solution knowledge graph which is a structured knowledge to derive answers. In this method, utterance collections of the same answering method are extracted and structured from the viewpoint of their effectiveness based on annotations attached by the participants. In addition, the structure of the solution knowledge graph is refined by evaluation of learners who use it as knowledge to solve exercises. We have constructed the prototype system for utilizing the solution knowledge graph in individual learning. From the experimental result, our system was reorganizing the solution knowledge graph according to the effectiveness of the utterance collections.