| Project/Area Number |
26350289
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | Tokyo University of Technology |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
安藤 公彦 東京工科大学, 片柳研究所, 助教 (00551863)
松永 信介 東京工科大学, メディア学部, 准教授 (60318871)
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,810,000 (Direct Cost: ¥3,700,000、Indirect Cost: ¥1,110,000)
Fiscal Year 2016: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2015: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2014: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | スクリプト / コンピュータ支援協調学習 / 教育データ / 深層学習 / コーディング / CSCL / 協調スクリプト / ディープラーニング / 学習データ |
|---|
| Outline of Final Research Achievements |
In the area of Computer Supported Collaborative Learning (CSCL) research, scripting collaborative learning is a relatively new but promising approach to promote learning. The term scripting is used to describe ways of prescribing relevant elements for collaborative interaction.In this research, the goal was to evaluate the effectiveness of multiple collaborative scripts for a large number of learners.
However, as a prerequisite, it was necessary to establish an analytical method capable of performing qualitative analysis of large-scale learning data in combination with quantitative methods. Therefore, we developed a method to automate coding to conversation using deep learning technology and evaluated its accuracy. As a result, our method realized the accuracy rate exceeding the baseline of machine learning, and it has become possible to perform qualitative analysis of large scale big data in a simple manner.
|
