Evaluation of Discussion Knowledge Graph for Organizing Collaborative Learning Record

ID: 22581 Type: Full Paper: Systems & Resources
  1. Tomoko Kojiri, Masahide Kakehi, and Toyohide Watanabe, Nagoya University, Japan

Thursday, July 3 4:40 PM-5:10 PM Location: FH 104 (5th Fl)

Presider: Dirk Schneckenberg, ESC Rennes School of Business, France

Abstract: Collaborative learning records includes heuristic knowledge to solve the exercise: hints and answers. Such knowledge is effective for a self-learning student who tackles the same exercise by himself. However, the collaborative learning records also contain many utterances that are not effective to solve the exercise. In this paper, discussion knowledge graph is introduced which consists of knowledge generated during the collaborative learning. Knowledge is extracted from effective utterances in the discussion record and answers described in private learning spaces of students. They are organized by their target answering steps based on annotations that are attached by students during the collaborative learning. Based on the annotations, utterances/answers that are heuristically effective to solve exercises can be extracted and organized automatically. In this paper, the construction method of the discussion knowledge graph is addressed and the result of its evaluation is described.


Conference attendees are able to comment on papers, view the full text and slides, and attend live presentations. If you are an attendee, please login to get full access.