Study on Personal Values-based User Modeling for Extending Applicability of Recommendation
| Project/Area Number |
16K12535
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Web informatics, Service informatics
|
|---|
| Research Institution | Tokyo Metropolitan University |
|---|
Principal Investigator |
Takama Yasufumi 首都大学東京, システムデザイン研究科, 教授 (20313364)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
服部 俊一 一般財団法人電力中央研究所, エネルギーイノベーション創発センター, 主任研究員 (00771916)
小野田 崇 青山学院大学, 理工学部, 教授 (40371661)
|
|---|
| Project Period (FY) |
2016-04-01 – 2020-03-31
|
| Project Status |
Completed (Fiscal Year 2019)
|
| Budget Amount *help |
¥3,510,000 (Direct Cost: ¥2,700,000、Indirect Cost: ¥810,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 推薦システム / 価値観 / 健康増進 / 観光 |
|---|
| Outline of Final Research Achievements |
This research aims to establish the method for modeling users' personal values, which will contribute to the extension of the applicability of recommendation. Personal values are defined as one's judgment of what is important in one's life. As a more suitable and quantitative definition for the recommendation, we have proposed the rate matching rate (RMRate). In this research, we studied the method for modeling users' personal values using RMRate and the recommendation methods based on the obtained user models. The experimental results show the proposed methods are effective for long-tail item recommendation. We have also studied to extend the target of recommendation from item recommendation to action recommendation. We have developed several recommender systems for health promotion and sightseeing.
|
| Academic Significance and Societal Importance of the Research Achievements |
現状の情報推薦技術では，少人数のユーザにしか購入，高評価されないロングテールアイテムの推薦は困難であることが知られている．また，健康増進のためのレシピ推薦や，エネルギー問題解決のための省エネ活動推薦などに情報推薦の適用範囲を拡大するためには，ユーザの行動変容を促す必要がある．すなわち，ユーザがこれまでとってきた行動とは異なる行動を推薦し，かつその推薦を受け入れてもらう必要がある．これは，ユーザの過去の行動からその嗜好を推測し，推薦アイテムを決定する従来アプローチでは対処が困難である．本研究で取り組んだ価値観モデリング，行動推薦に関する研究成果はこれらの課題解決に貢献することが期待できる．
|
Report
(5 results)
Research Products
(58 results)
