| Project/Area Number |
25282086
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Partial Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Social systems engineering/Safety system
|
|---|
| Research Institution | Keio University (2015)
University of Tsukuba |
|---|
Principal Investigator |
SUMITA Ushio 慶應義塾大学, 経営管理研究科, 特任教授 (10236044)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
OKADA Masahiro 慶應義塾大学, 経営管理研究科, 教授 (70327667)
HAYASHI Takaki 慶應義塾大学, 経営管理研究科, 教授 (80420826)
HACHIMORI Masayasu 筑波大学, システム情報系, 准教授 (00344862)
TAKEHARA Kota 筑波大学, システム情報系, 助教 (70611747)
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥8,320,000 (Direct Cost: ¥6,400,000、Indirect Cost: ¥1,920,000)
Fiscal Year 2015: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2014: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
Fiscal Year 2013: ¥3,380,000 (Direct Cost: ¥2,600,000、Indirect Cost: ¥780,000)
|
|---|
| Keywords | ビッグ・データ解析 / ブログ・プロファイル・ベクター / プロダクト・プロファイル・ベクター / テキスト・マイニング / 判別アルゴリズム / 将来値予測アルゴリズム / スマートフォン応用ソフト / VOC（Voice of Customers) / ビッグデータ解析 / 製品組合せ販売 / VOC (Voice of Customers) / アクセスログ / プロファイル・ベクター / テキストマイニング / 単語・文章スコア / スマートフォン応用アプリ / 浸透度 / 安定度 / ダウンロード数 / 予測アルゴリズム / マルコフ連鎖 / 相補的関係 / 相殺的関係 / セキュリティー / ダウンロード数予測アルゴリズム / マルコフ解析 |
|---|
| Outline of Final Research Achievements |
The purpose of this research was to establish a systematic approach for analyzing how e-WoM (e-Word-of Mouth) may affect performances of products and services on the Internet. With focus on digital cameras and movies, an ambitious attempt was made to conduct a comparative analysis between the United States and Japan, which remains incomplete because of the difficulty to create a common dictionary for text mining across English and Japanese. The project was quite successful, however, in the study of smartphone applications in Japan, where new knowledge was created concerning popularity, stability, security risk, prediction of the number of downloads, competitive or complementary relationships and the like. The validity of the proposed approach was also demonstrated by applying it to problems surrounding big data analytics in several different areas.
|
