Review recommendation based on the automatic scoring mechanism to each evaluation aspect
| Project/Area Number |
16K00425
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Web informatics, Service informatics
|
|---|
| Research Institution | University of Marketing and Distribution Sciences |
|---|
Principal Investigator |
UEDA Mayumi 流通科学大学, 経済学部, 教授 (30402407)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
中島 伸介 京都産業大学, 情報理工学部, 教授 (90399535)
|
|---|
| Project Period (FY) |
2016-04-01 – 2019-03-31
|
| Project Status |
Completed (Fiscal Year 2018)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2016: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 口コミ情報推薦 / レビュー推薦 / レビュー分析 / 評価値自動付与 / 類似ユーザ判定 / 価値観 / 口コミ分析 / タグ推薦 / 情報システム |
|---|
| Outline of Final Research Achievements |
The purpose of this study is to develop a recommender system for cosmetic items and reviews to help consumers. In order to realize such recommender system, we developed a method for automatic scoring of various aspects of cosmetic items based on evaluation expression dictionary. Then, we studied a method to find similar users based on their preferences against cosmetic item clusters. Our system recommends cosmetic items which is evaluated high score by the similar user. In order to find the similar user, our system calculates the user similarity based on the evaluation for each aspect by users. Moreover, we studied a method to recommend truly useful reviews for each target user using scores of various aspects of cosmetic items.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究において，複数評価軸に対する評価値自動付与方式の実現により，自然言語による口コミ情報の中から，複数の評価軸に対する評価値を推定することにより，個人による評価のブレを排除し，アイテムに対する価値の全体像を把握することが可能となる．また，口コミ情報分析に基づく類似ユーザ判定手法の実現により，膨大な量の口コミ情報から，価値観の共有可能なユーザによって投稿された，閲覧者にとって真に有用となる口コミ情報を効率的に入手することが可能となる．本研究では，個人の意思決定に大きな影響を与えている口コミ情報を個人の価値観に沿って提供可能な仕組みを実現しており，社会的な意義は大きい．
|
Report
(4 results)
Research Products
(18 results)
-
-
[Journal Article] Mining Attribute-Specific Ratings from Reviews of Cosmetic Products2017
Author(s)
Yuuki Matsunami, Mayumi Ueda, Shinsuke Nakajima, Takeru Hashikami, John O'Donovan, Byungkyu Kang
-
Journal Title
Transactions on Engineering Technologies, (International MultiConference of Engineers and Computer Scientists 2016)
Volume: -
Pages: 101-114
DOI
ISBN
9789811039492, 9789811039508
Related Report
Peer Reviewed / Int'l Joint Research / Acknowledgement Compliant
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] A Cross-Cultural Analysis of Explanations for Product Reviews2016
Author(s)
John O'Donovan, Shinsuke Nakajima, Tobias Hollerer, Mayumi Ueda, Yuuki Matsunami, Byungkyu Kang
Organizer
Joint Workshop on Interfaces and Human Decision Making for Recommender Systems(IntRS 2016) co-located with ACM Conference on Recommender Systems (RecSys 2016)
Place of Presentation
Boston(USA)
Year and Date
2016-09-16
Related Report
Int'l Joint Research
