The Impact of Recommendation System on User Satisfaction: A Moderated Mediation Approach

Abstract

A recommendation system serves as a key factor for improving e-commerce users’ satisfaction by providing them with more accurate and diverse suggestions. A significant body of research has examined the accuracy and diversity of a variety of recommendation systems. However, little is known about the psychological mechanisms through which the recommendation system influences the user satisfaction. Thus, the purpose of this study is to contribute to this gap by examining the mediating and moderating processes underlying this relationship. Drawing from the traditional task-technology fit literature, the study developed a moderated mediation model, simultaneously considering the roles of a user’s feeling state and shopping goal. We adopted a scenario-based experimental approach to test three hypotheses contained in the model. The results showed that there is an interaction effect between shopping goals and types of recommendation (diversity and accuracy) on user satisfaction. Specifically, when a user’s shopping goal aligns with recommendation results in terms of accuracy and diversity, the user satisfaction is enhanced. Furthermore, this study evaluated the mediating role of feeling right and psychological reactance for a better understanding of this interactive relationship. We tested the moderated mediation effect of feeling right and the psychological reactance moderated by the user shopping goal. For goal-directed users, accurate recommendations trigger the activation of feeling right, consequently increasing the user satisfaction. Conversely, when exploratory users face accurate recommendations, they activate psychological reactance, which leads to a reduction in user satisfaction. Finally, we discuss the implications for the study of recommendation systems, and for how marketers/online retailers can implement them to improve online customers’ shopping experience.