Motivation-Based Museum Personalization: Adaptive Artifact Descriptions with Large Language Models

Museums increasingly adopt digital technologies to enhance visitor engagement, yet artifact descriptions often fail to accommodate diverse motivations and attention patterns. Large language models (LLMs) offer opportunities for adaptive and personalized interpretation, but existing approaches frequently rely on privacy-invasive behavioral tracking. We explore how LLMs can support privacy-preserving personalization of artifact descriptions based on visitor motivation profiles. We developed a system that adapts tone, complexity, and narrative style using a questionnaire grounded in Falk’s Museum Visitor Experience Model. An exploratory user study with 21 participants was conducted in situ at a museum using a mobile web-based prototype, comparing engagement with adapted and original artifact descriptions. Results indicate that AI-adapted descriptions were frequently perceived as engaging, and qualitative feedback showed that motivation-based adaptations resonated more personally with many participants. While the profiling instrument received preliminary convergent validation, full psychometric validation remains an important direction for future work. The study provides insights for designing personalized, privacy-preserving, and mobile AI-adaptive content in museum contexts.