High quality content mining using collective intelligence
| Project/Area Number |
23500299
|
|---|
| 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 | Kyushu University |
|---|
Principal Investigator |
ITO Eisuke 九州大学, 学内共同利用施設等, 准教授 (90294991)
|
|---|
| Project Period (FY) |
2011 – 2013
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥5,070,000 (Direct Cost: ¥3,900,000、Indirect Cost: ¥1,170,000)
Fiscal Year 2013: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2012: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2011: ¥2,340,000 (Direct Cost: ¥1,800,000、Indirect Cost: ¥540,000)
|
|---|
| Keywords | 情報検索 / コンテンツ検索 / consumer generated media / 集合知 / sentiment analysis / semantic analysis / リンク構造 / ランキング / カテゴリ自動分類 / 動画コメント / 感情語分析 / 国際情報交換 / コンテンツ / 利用者参加型 |
|---|
| Research Abstract |
A large number of contents are being uploaded as online novels. I proposed two ranking methods. One is based on viewer's sentimental comments, and the other is based on the users' favorite lists (bookmarks). Relation between users and favorites can be represented as a bipartite graph. In several genres, the later one can predict future popular contents.
I studied semantic hierarchization of tags, which is given by many users. The hierarchy is based on frequency and co-occurrence of tags, and a hierarchy is represented as a direct acyclic graph. However, the automatic generation of tag hierarchy is not enough for automatic categorization. More careful study is need for automatic categorization.
|
Report
(4 results)
Research Products
(26 results)
