| Project/Area Number |
21700268
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Library and information science/Humanistic social informatics
|
|---|
| Research Institution | University of Tsukuba (2010-2011)
Toyohashi University of Technology (2009) |
|---|
Principal Investigator |
SEKI Yohei 筑波大学, 図書館情報メディア系, 助教 (00348468)
|
|---|
| Project Period (FY) |
2009 – 2011
|
| Project Status |
Completed (Fiscal Year 2011)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2011: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2010: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2009: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | 情報検索 / コミュニティQA / 良質回答の予測 / 情報要求の言語化 / コーパスと意見分析 / アンサンブル学習 / 関係推定 / 顔文字推薦 / 機械翻訳 / ブログ / アプレイザル理論 / 多言語辞書 / 多言語意見分析タスク / 意見情報 / 社会調査型質問 / 回答意見検索 / 文書ジャンル横断 / 意見タイプ / 質問タイプ |
|---|
| Research Abstract |
In this research, we annotated opinion and opinion targets using Yahoo! Blog corpus and found that opinions were characterized with domains such as computer, entertainment, or politics. We also proposed opinion extraction system toward multiple domains based on ensemble learning. In NTCIR-8, we conduct multilingual opinion analysis task to evaluate opinion extraction technologies in Japanese, English, and Chinese. We also extended English appraisal dictionary toward Japanese dictionary and experimented opinion extraction in Japanese and English using two dictionaries. We also focused community question answering contents (CQA) to extract and summarize user opinions, and proposed good answer estimation and query expansion type Web retrieval systems. Finally, we proposed communication supporting systems mediating personal opinions such as : (1) facemark recommendation system based on emotion estimation using microblogs, (2) relation estimation system toward personal names and surrounding entities, and (3) example-based machine translation system using alignment clues in parallel multilingual corpus.
|
