Web Advertising Recommender System Based on Estimating Users' Latent Interests

2020 Fiscal Year Final Research Report

• Project/Area Number: 17H01822
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Single-year Grants
• Section: 一般
• Research Field: Web informatics, Service informatics
• Research Institution: Kyoto Sangyo University
• Principal Investigator: NAKAJIMA Shinsuke 京都産業大学, 情報理工学部, 教授 (90399535)
• Co-Investigator(Kenkyū-buntansha): 河合 由起子 京都産業大学, 情報理工学部, 教授 (90399543) ; 張 建偉 岩手大学, 理工学部, 准教授 (20635924)
• Project Period (FY): 2017-04-01 – 2021-03-31
• Keywords: 広告推薦技術 / 潜在的興味分析

Outline of Final Research Achievements

In this research project, we tried to develop a Web ad recommender system based on latent interest analysis considering users’ sentiments and contexts, with analyzing user behavior in cyber space and physical space. As for estimating users' interests in cyber space, we tried to develop a method that enables analysis of not only users' direct and explicit interests estimated from past Web browsing histories but also latent interests. As for estimating users' latent interests in physical space, we tried to develop a method for analyzing users' explicit and latent interests based on geo-tagged tweets analysis, as well as behavior prediction method using physical space users’ behavior histories. In addition, we tried to develop an interest analysis method and spot recommendation technique for users' activities such as walking in physical space.

Free Research Field

情報推薦技術の開発

Academic Significance and Societal Importance of the Research Achievements

本研究の成果である，Web 空間と実空間双方の行動分析からより詳細なユーザの興味分析を行う点，直接的・明示的興味だけでなく潜在的興味を持つ購買層を特定しWeb 広告を推薦しようとする点において，その独創性・新規性が高く，学術的意義も大きいといえる．
また，本研究課題は研究協力者であるWeb 広告企業との連携に基づいて行ったものである．実際にサービスを行っている企業と連携することで，従来サービスの問題点や課題を把握した上で研究を遂行するため，実サービスに即時活用可能な技術の開発が期待できる点において社会的意義も高いといえる．