| Project/Area Number |
16K16331
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | Tokyo Metropolitan University |
|---|
Principal Investigator |
Kondo Nobuhiko 首都大学東京, 大学教育センター, 准教授 (10534612)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,900,000 (Direct Cost: ¥3,000,000、Indirect Cost: ¥900,000)
Fiscal Year 2018: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2017: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 機械学習 / 教学IR / 予測モデル / 確率モデル / 修学状態 / 学習支援 / ラーニングアナリティクス / 教育工学 |
|---|
| Outline of Final Research Achievements |
In this research, with the aim of providing appropriate learning support according to each student by using educational big data, modeling of students' learning states by machine learning method and learning support using such models were examined. Based on the students' data held by a university, usefulness of some modeling methods were examined by numerical experiments. By using well-known algorithms such as Bayesian networks and random forests, the transition of learning states were modeled and the prediction models of learning outcomes were constructed, and modeling with a certain accuracy was shown to be possible. In addition, a modeling framework based on the particularity of educational data in universities was proposed, and the research results as general findings were summarized.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究成果は、汎用的な確率モデルとして知られるベイジアンネットワークを用いた大学生の修学状態の推移のモデル化のフレームワークの提案、機械学習による学習成果の予測モデルを構築することについての数値的な検証、の2つに大きくまとめられる。これらに共通するのは、「どのような大学にも対応できるモデル」ではなくそれぞれの大学の状況に応じた「モデル構築の方法論」について提案したことと、学期ごとの成績のような粒度の粗いデータと学習管理システムのログのような粒度の細かいデータをあわせて用いることの可能性について検討を行ったことであり、実際の大学の現場での活用に向けた知見をまとめたことに意義があると考えられる。
|
