Understanding Consumer Behavior Through AI-Powered Recommender Systems : A Systematic Review and Bibliometric Perspective

Purpose : This study examined the evolving landscape of recommender systems (RSs) and their impact on consumer purchasing behavior by identifying key research themes, trends, and gaps in the current literature. Methodology : A bibliometric analysis and systematic literature review (SLR) of 312 articles was conducted using the R package to perform performance analysis and scientific mapping, aiming to investigate the intellectual framework of the field, emerging issues, and research trends. Findings : The study identified four prominent themes: the role of RSs and AI in consumer decision support, trust, and adoption; the consumer privacy paradox in personalized commerce; and communication strategies in web personalization. The research indicated a shift toward adaptive, emotionally intelligent, and privacy-conscious RSs. Practical Implications : The results provided crucial insights for platform practitioners and developers to create RSs that enhanced personalization while addressing key issues related to trust, privacy, and user engagement, thereby improving the consumer experience and retention. Originality : This paper offered a comprehensive and organized summary of the fragmented literature on RSs and consumer behavior. By integrating bibliometric analysis with an SLR presented a unique, data-driven framework for future academic exploration and responsible innovation in digital commerce.