Development of group recommendation system based on discussions among multiple people and robots

2021 Fiscal Year Final Research Report

• Project/Area Number: 20K23344
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 1002:Human informatics, applied informatics and related fields
• Research Institution: Osaka University
• Principal Investigator: SAKAI KAZUKI 大阪大学, 基礎工学研究科, 特任助教(常勤) (80879445)
• Project Period (FY): 2020-09-11 – 2022-03-31
• Keywords: 対話ロボット / 集団推薦 / 選好モデル / 議論システム / 複数人対話システム

Outline of Final Research Achievements

In this research, we developed a group recommendation system that is easy to accept the recommendation based on a multiple robots’ discussions for multiple participants. We constructed a preference model that included the various aspects of topics. In addition, we implemented a multiple robots’ system that recommended an item based on the preference model in the conversation where the robots asked participants’ preferences and experiences. We confirmed that the acceptance ratio and agreement were improved by the group recommendation in the field experiment.

Free Research Field

知能ロボティクス

Academic Significance and Societal Importance of the Research Achievements

本研究では，複数ロボット議論システムを用いた，納得感の高い集団推薦システムの開発に取り組んだ．集団の性質を利用した集団推薦ロボットの開発を通して，集団化することによる人間のふるまいの変化という認知的な側面を明らかにした点に意義がある．複数人が参加する推薦は日常的な場面においてよく見られる行為であり，本研究はロボットの普及を進めていくうえで重要な役割を果たしていると考えられる．