A review recommendation method based on user preference similarity analysis using item evaluation score for various aspects

2023 Fiscal Year Final Research Report

• Project/Area Number: 19K12243
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 62020:Web informatics and service informatics-related
• 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): 2019-04-01 – 2024-03-31
• Keywords: 情報推薦 / レビュー分析 / 評判分析 / ユーザ間類似度 / 相違点可視化

Outline of Final Research Achievements

The purpose of this project is to develop a review recommendation system based on the analysis of user similarity using an automatic scoring method for various aspects. To realize such a review recommendation system, we try to identify users who not only have similar overall evaluations of items but also share similar detailed evaluations and values by estimating values for various evaluation aspects from review information based on free descriptions. We consider that the implementation of our proposed method will make it possible to provide effective review information for each users.

Free Research Field

情報推薦

Academic Significance and Societal Importance of the Research Achievements

本研究課題では，自由記述によるレビュー情報から，複数評価軸に対する評価を推定し，価値観の共有可能なユーザを特定するという点に注目して取り組んでおり，学術的意義は大きいと考える。また，目的や状況に応じて有益となるレビュー情報の提示方法についても検討しており，消費者が意思決定の際にレビュー情報を参考にすることが多い時代に合った取り組みである。