Behavioral Analysis of AI-Assisted User Interaction in a Digital Art Repository

Recent developments in artificial intelligence, including the emergence of generative AI and large language models, have brought changes to user interaction habits as well as interface design. These emerging technologies can be integrated into digital art repositories to reshape interaction paradigms through content enrichment, context-based recommendations, natural-language querying and automated artwork classification. As this landscape evolves, it is important to understand how these changes are reflected in user behavior. In this study, we present a comparative behavioral evaluation based on two versions of a publicly available digital repository for academic artworks: a traditional version and one incorporating a series of AI-powered features. A mixed factorial design with task counterbalancing was used to evaluate user behavior through an approach combining platform analytics, self-reported metrics and qualitative insights. This exploratory analysis identified feature-dependent differences in participants’ behavior and perceptions, and yielded preliminary observations that can inform large-scale research. Understanding how users perceive and engage with AI features can allow content providers to make informed decisions regarding their integration and streamline user interactions while remaining aligned with stakeholder expectations.