Information Seeking Behavior Suggestion System using Collaborative Reference Database
| Project/Area Number |
25540150
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Library and information science/Humanistic social informatics
|
|---|
| Research Institution | Doshisha University |
|---|
Principal Investigator |
HATANO Kenji 同志社大学, 文化情報学部, 准教授 (80314532)
|
|---|
| Project Period (FY) |
2013-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2014: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2013: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
|
|---|
| Keywords | 検索行動補助 / ルールマイニング / 知識ベース / 知識ベース化 / 係り受け関係 / 自動抽出 |
|---|
| Outline of Final Research Achievements |
In this research, we propose a method for suggesting information seeking behavior to search engine users using Collaborative Reference Database operated by National Diet Library (NDL). The reason why we do not utilize access log of search engines is that Collaborative Reference Database includes IT specialist's searching procedures to get useful information, so that it is useful for the search engine users to show them, we think. As a result, the search engine users can learn how to access such the useful information to emulate the capabilities of the IT specialist without their knowledge.
One of the most impressive research outcome is our novel dependency parsing method based on hierarchical structure of Japanese Language. It can help to precisely extract information seeking behaviors from Collaborative Reference Database compared with conventional approaches.
|
Report
(3 results)
Research Products
(10 results)
