Research on prediction of learning behavior and status based on comments written by students
| Project/Area Number |
25350311
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | Kyushu Institute of Information Sciences |
|---|
Principal Investigator |
Goda Kazumasa 九州情報大学, 経営情報学部, 准教授 (50320396)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
MINE Tsunenori 九州大学, システム情報科学研究科(研究院, 准教授 (30243851)
ISHIOKA Tsunenori 独立行政法人大学入試センター, その他部局等, 教授 (80311166)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2015: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 教授学習支援システム / 学習行動評価 / 学習状況評価 / コメント分析 |
|---|
| Outline of Final Research Achievements |
We attempted to grasp the learning behavior and situation based on seld evaluated descriptions, which are written by the learners themselves. In this study we have automated the analysis procedure that was previously performed manually. At that time we introduced a new indication "PCN score", and we predicted the final grade. As a result, we obtained maximum value of 0.71 as accuracy which was culculated by P score.
In order to improve the accuracy, we have tried various method of machine learning, we showed that we can acquire the F1 value of about 95 %. We also use understanging, cooperating, effort to review and prepare as another items for analysis which are inspired from PCN items, and we clarified the features of the new item values corresponding to the final grade.
|
Report
(4 results)
Research Products
(23 results)
