A Operable Recommender System with Presenting Reason of Recommendation and Prediction Information

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K16091
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Web informatics, Service informatics
• Research Institution: Kogakuin University
• Principal Investigator: Kitayama Daisuke 工学院大学, 情報学部(情報工学部), 准教授 (40589975)
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: 推薦システム / ユーザ行動

Outline of Final Research Achievements

By working on the following two themes, we developed a user-operable information recommendation system that presents reasons for recommendation and predictive information.
(A) The following study was conducted as a manifestation of reasons for recommendation based on user behavior patterns. (1) Research on the recommendation system that can clearly indicate the reason for recommendation. (2) Study on diversification of the reason for recommendation. (3) Study on the effect of clarification of recommendation reason.
(B) The following system was developed as a prediction of the recommended direction based on user selection operation. (1) Sightseeing spot search / recommendation method based on user's review selection. (2) Judgment of reaching probability and editing support method based on retweet pattern. (3) Search navigation system based on similarity between coordination using user tag of coordination posting site.

Free Research Field

メディア情報学