Construction of customers' emotion model in the bespoke tailoring using evaluation grid method

To realize a recommendation system that combines the benefits of human recommendation (experts in the field, e.g., salesclerks) and computer recommendation (recommendation algorithms, such as those in e-commerce), we constructed an emotion model that appropriately represents customers' emotions during a human recommendation process. As a typical scene of a recommendation by a human, we focused on bespoke tailoring in which a customer interacts with a tailor. First, we extracted emotions evoked in the scene using the evaluation grid method. After that, we constructed an emotion model by determining the extracted emotions' positions on the core affect model. As a result, we constructed an emotion model that appropriately expressed the emotions evoked in the recommendation process. In addition, we found that unique emotions such as troubled and expected are evoked in the recommendation by a human.