Analyzing Microblog Articles based on Text Understanding
| Project/Area Number |
24500296
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Library and information science/Humanistic social informatics
|
|---|
| Research Institution | Okayama Prefectural University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
TAJIMA Yasuhiro 岡山県立大学, 情報工学部, 准教授 (00334467)
|
|---|
| Project Period (FY) |
2012-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2013: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2012: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | ウエブマイニング / テキストマイニング / 自然言語解析 / マイクロブログ / テキスト解析 / 自然言語理解 / 自然言語処理 |
|---|
| Outline of Final Research Achievements |
This work has two major results. One result relates to parsing micro-blog sentences. Since micro-blog articles often lacks sentence boundary markers, we first developed sentence boundary detector by using machine learning technique applied to word/character sequences. Then, we developed dependency analyzer including base phrase (so-called bunsetsu) chunker. Experimental results show our method outperforms existing software by 10 points. The other result is on trend analysis for micro-blog articles. We have developed a method for choosing an article which best describes a given burst word. The method applies sentence extraction to articles within the automatically identified burst period (for the given word).
|
Report
(5 results)
Research Products
(6 results)
