| Project/Area Number |
16K12559
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Learning support system
|
|---|
| Research Institution | Kyushu Institute of Technology |
|---|
Principal Investigator |
Inoue Sozo 九州工業大学, 大学院生命体工学研究科, 准教授 (90346825)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
馬場 雪乃 筑波大学, システム情報系, 准教授 (40711453)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | eラーニング / クラウドソーシング / 機械学習 / eテスト / e-ラーニング |
|---|
| Outline of Final Research Achievements |
In this research, we studied crowdsourcing technology for e-test. While having a large number of people create test questions, we adopted an algorithm and system to estimate the quality and the score to the answer appropriately by machine learning and natural language processing. Since we could get some results by the start of the research and was able to be published in a international conference and operate the actual system, we worked on various issues in crowdsourcing during the research period. We proposed a gamification that raises the score in a direction that can improve the quality of data, a method of using machine learning to collect data using a dialogue system, zero shot learning to classify classes which are not included in training data.
|
| Academic Significance and Societal Importance of the Research Achievements |
eテストにおいては問題を作る側のコストが大きくなるため、そのタスクをクラウドソーシングすると同時に品質を確保するコン研究の意義は大きい。実際に動作するWebシステムも開発したため、これらをeラーニングに展開することも今後容易である。このシステムを普及させて、人工知能に負けない人間の知能形成を行なっていきたい。
|
