Project/Area Number |
26560134
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Multi-year Fund |
Research Field |
Educational technology
|
Research Institution | National Institute of Informatics |
Principal Investigator |
Sun Yuan 国立情報学研究所, 情報社会相関研究系, 准教授 (00249939)
|
Co-Investigator(Renkei-kenkyūsha) |
TOYOTA Tetsuya 青山学院大学, 理工学部情報テクノロジー学科, 助教 (30650618)
SUZUKI Masayuki 横浜国立大学, 教育学部, 講師 (00708703)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2014: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
Keywords | 学習診断 / 学習ログ / 認知診断テスト / フィードバック / 学習ログデータ / 認知診断 / 学習支援 |
Outline of Final Research Achievements |
In this study, we constructed an e-learning system implemented with learning contents and cognitive diagnostic tests and gathered variety of learning log data. We proposed methods for clustering learning patterns and predicting learners’ behaviors based on their learning log. To investigate how learners use feedback information, eye movements of the learners were analyzed to examine the effects of the type of feedback and learners’ achievement goals on the manner in which feedback information was reviewed. The key issue affecting cognitive diagnostic models is how to specify attributes and the Q-matrix. In this study we used the Boolean matrix factorization method to express conjunctive models and proposed a new theoretical framework for data-driven Q-matrix learning. We also proposed effective heuristic approximation algorithms for Q-matrix learning and learners’knowledge states estimation from their observable item response patterns.
|