Opinion Mining from Texts Including Quoted Others' Opinions
| Project/Area Number |
17K00298
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Japan Advanced Institute of Science and Technology |
|---|
Principal Investigator |
Shirai Kiyoaki 北陸先端科学技術大学院大学, 先端科学技術研究科, 准教授 (30302970)
|
|---|
| Project Period (FY) |
2017-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2018: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | オピニオンマイニング / 極性判定 / 機械学習 / テキストの極性判定 / 自然言語処理 |
|---|
| Outline of Final Research Achievements |
This research project aims at the polarity classification of texts (blog articles) including quotation of other articles toward opinion mining of social issues. First, a quoted text is extracted from a given blog article. Next, the polarity of a text written by a user and a quoted text written by others is identified. Then, a quotation type (“agree”, “disagree”, or “unrelated”) is identified, which stands for relation between the original and quoted texts. Finally, the polarity of the whole blog article is determined by considering the above results. In the experiments, the accuracy of the polarity classification of the proposed method was 0.942, which largely outperformed the baseline (0.893).
|
| Academic Significance and Societal Importance of the Research Achievements |
不特定多数のユーザが書いたテキストから特定の対象に対するユーザの意見や評判を明らかにするオピニオンマイニングは重要な研究課題である．特に時事問題を対象にしたオピニオンマイニングは，社会情勢を低コストで把握することができるため有用である．本研究課題は，他者の記事の引用を含むテキストの極性判定の精緻化によりオピニオンマイニングの正確性を向上させるものであり，その社会的意義は大きい．
これまでの極性判定の研究では，判定対象となるテキストの部分の性質の違いに着目した研究は少ない．本研究課題は，引用されたテキストとそうでないテキストを分けて処理することで極性判定の性能を向上させる点に学術的意義がある．
|
Report
(4 results)
Research Products
(3 results)
