Artographer: a Curatorial Interface for Art Space Exploration
For designers of digital art platforms and media distribution systems, this work provides a novel interface and empirical insights that challenge dominant recommendation paradigms, though the findings are exploratory and domain-specific.
The paper introduces Artographer, a zoomable 2-D map interface for exploring ~16,000 historical artworks via similarity-clustered embeddings, and evaluates it with 20 participants including 9 art history scholars. It identifies four values (Visibility, Agency, Serendipity, Friction) that challenge recommendation system paradigms and proposes a curatorial approach to media distribution.
Relating a piece to previously established works is crucial in creating and engaging with art, but AI interfaces tend to obscure such relationships, rather than helping users explore them. Embedding models present new opportunities to support spatially exploring and relating artwork. We built Artographer, an art-exploration system featuring a zoomable 2-D map, constructed from similarity-clustered embeddings of ~16,000 historical artworks. We used Artographer as a design probe to explore how alternative artwork distribution interface design can shape media engagement: we invited 20 participants, including 9 art history scholars, to traverse the map, collecting artworks for a goal-driven task and while freely exploring. We identify values enacted in spatial art discovery (Visibility, Agency, Serendipity, Friction) and consider how these values challenge dominant design paradigms -- in particular, the recommendation systems governing contemporary media distribution platforms. We reimagine a curatorial approach to media distribution, within digital ecosystems where history and culture can thrive.