Value-Aware Recommender Systems for Strategic Intelligence in Digital Cultural Ecosystems

Digital cultural platforms increasingly rely on recommender systems to support access to and engagement with large-scale heritage collections, yet their potential as instruments of strategic intelligence remains underexamined. This study conceptualizes and empirically evaluates value-aware recommender systems as strategic intelligence infrastructures in digital cultural ecosystems. Using a design science research approach and comparative evaluation, a multimodal recommender framework integrating diversity, inclusion, visibility, and strategic priority signals was developed and tested on large-scale open datasets from Europeana, Rijksmuseum, and The Metropolitan Museum of Art. The value-aware model maintains comparable recommendation accuracy while substantially improving cultural representation and visibility balance. Diversity increased by 27%, coverage by 34%, and minority representation from 0.18 to 0.31, while visibility disparities decreased by 38% and the Cultural Representation Score improved from 0.62 to 0.84. Cross-platform and multilingual analyses confirm the robustness of the approach. The results demonstrate that value-aware recommender systems can function as data-driven strategic intelligence tools that support cultural organizations in enhancing visibility, diversity, and evidence-based decision-making.