| Project/Area Number |
26590113
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Social welfare and social work studies
|
|---|
| Research Institution | The University of Kitakyushu |
|---|
Principal Investigator |
NAKAO Yasushi 北九州市立大学, 基盤教育センター, 教授 (60309531)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
浅羽 修丈 北九州市立大学, 基盤教育センター, 准教授 (50458105)
|
|---|
| Project Period (FY) |
2014-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2016: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2015: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2014: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
|
|---|
| Keywords | 困窮者支援 / データベースシステム / 機械学習 |
|---|
| Outline of Final Research Achievements |
In the support activities for needy persons, a database system is operated for recording daily support contents. Support contents are classified into several items by contents manually in such system.In this research, we aimed to develop a system to automatically classify support contents entered by supporters.The method we used is "latent semantic analysis by topic model" in the field of machine learning. As a result, we found that there are support contents that can be classified with relatively high accuracy. However, support contents that can not be classified very well also exist. In order to actually use the system at the site of support, it is necessary to improve the accuracy of our system.
|
