| Project/Area Number |
18500194
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
情報図書館学・人文社会情報学
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
YORO Shin-ichi Osaka University, Graduate School of Law and Politics, Associate Professor (30240831)
|
|---|
| Project Period (FY) |
2006 – 2007
|
| Project Status |
Completed (Fiscal Year 2007)
|
| Budget Amount *help |
¥3,930,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥330,000)
Fiscal Year 2007: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2006: ¥2,500,000 (Direct Cost: ¥2,500,000)
|
|---|
| Keywords | Legal Information / Machine Learning / Automatic Classification / SVM |
|---|
| Research Abstract |
We can obtain a lot of legal information by retrieving the Internet, but usually it contains a lot of needless information. If we can automatically classify information into legal information and other information, we can efficiently retrieve legal information. We tried to automatically classify it by using Support Vector Machine Algorithm.
In 2006, we developed the experiment system of automatic document classification to support our research. This system learns the features of the documents that have already been classified into some categories. And then it can classify a document based on the learning result.
In 2007, we experimented on an automatic classification of legal documents. We tried to classify documents into law information and other information, tried to classify legal documents into the decision sentences and the statutes, and tried to classify decision sentences into those of the criminal trials and those of the civil trials. In all cases, we could automatically classify documents with high accuracy. This result will leads to the development of the search engine that specializes in legal information.
|
