Project/Area Number |
15K00451
|
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, 情報基盤研究開発センター, 准教授 (90294991)
|
Project Period (FY) |
2015-04-01 – 2018-03-31
|
Project Status |
Completed (Fiscal Year 2017)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
Keywords | コンテンツ / CGM / 多様性 / 類似度 / 回帰分析 / 深層学習 / 類似度の総和 / 利用者投稿型コンテンツ / クラスタリング / 統計分析 / 対数正規分布 / 情報エントロピー |
Outline of Final Research Achievements |
This research aimed to (1) quantitative evaluation of content diversity trends in CGM (Consumer Generated Media), and (2) establishment of content selection model of users. Targeted CGMs are movies, novels and academic papers. In (1), I proposed three metrics for quantitative contents diversity. Using sum of similarity metric, I found that diversity are decreasing for movies and novels, but academic papers keep diversity. In (2), I found that pageview distribution is close to the log-normal distribution, but the distribution differs for each genre. As a result of regression analysis to estimate pageviews of contents, estimation accuracy was good, but establishment of the user's content selection model was incomplete.
|