Product Recommendation and Visualization Method based on Transition for Emotions of Potential Buyers

2022 Fiscal Year Final Research Report

• Project/Area Number: 18K04600
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 25010:Social systems engineering-related
• Research Institution: Hiroshima City University
• Principal Investigator: Kajiyama Tomoko 広島市立大学, 情報科学研究科, 准教授 (20454085)
• Project Period (FY): 2018-04-01 – 2023-03-31
• Keywords: 感情推定 / 購買行動 / 商品推薦 / 視線情報 / 色彩心理 / 商品パッケージ / 商品レビュー / 潜在顧客

Outline of Final Research Achievements

A product recommendation and visualization method were proposed based on transition for emotions of potential buyers. This research focused on the principle of color psychology that colors can be used to estimate people’s emotion, tried to estimate the emotion of potential buyers based on their clothing colors and gaze information during purchase activities, and recommended products that match the estimated emotion. The target object of this research was beverages. We created the abstract package images and constructed a beverage display system that could track gaze information by a web camera. By conducting a survey of purchasing activities using this system, we constructed a color database expressing the relationships between emotions and colors and a purchasing rule database expressing the relationships between emotions and purchased products. We confirmed that the number of potential buyers were increased by adding a recommendation function using these databases.

Free Research Field

情報検索，感性工学

Academic Significance and Societal Importance of the Research Achievements

従来の消費者行動分析による商品推薦では，売上データ，顧客特性，サイバー空間上の顧客の発言や閲覧商品などの解析により行われており，購買・投稿・閲覧情報が，現在も関心のある情報であるという仮定が前提であった．本研究では，潜在顧客の過去の興味ではなく，購買活動時における感情を考慮し，色彩と視線情報を活用することで商品推薦を行った．自身の感情をすり合わせやすくなる商品パッケージを生成する手法，色彩から感情を推定する方法，視線から人の関心を推定する手法，推定した感情から商品を推薦する手法の検討により，繊細に揺れ動く人の感情による商品ジャンルを超えた推薦が可能となった．