2012 Fiscal Year Final Research Report
Database creation of test-item's statistical information set and the statistical analysis using natural-language-processing technology
| Project/Area Number |
21300320
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | The National Center for University Entrance Examinations |
|---|
Principal Investigator |
ISHIOKA Tsunenori 独立行政法人大学入試センター, 研究開発部, 教授 (80311166)
|
|---|
| Project Period (FY) |
2008 – 2012
|
| Keywords | 自然言語処理 / 情報システム / 統計数学 / 人工知能 |
|---|
| Research Abstract |
(1) We have built a comprehensive system which indicates national-center-test items linking their statistics stored in information database through our local network. Public and private university entrance examination test items can also be retrieved.
(2) Judging that the technology of recommendation system with natural-language-processing becomes one of the components of our subject, we verified the validity of the technique. As an empirical study, we use Random Forests to the scores of national center test, and announced the result to research meeting.
(3) Since convincing that Random Forests method should be recognized to one of the standards of the data-analysis technique containing missing data, we performed positive researches, such as an imputation of context information, and investigated the new technique. The results of research were presented at many refereed international research conferences.
|
