ARTLAS: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering

arXiv cs.AI / 4/1/2026

💬 OpinionIdeas & Deep AnalysisTools & Practical UsageModels & Research

共有:

Key Points

The paper introduces ARTLAS, a computational framework that maps 78 art-technology institutions using an eight-axis conceptual model spanning philosophy, geography, knowledge production, history, time orientation, ecosystem role, audience relation, and disciplinary positioning.
It encodes qualitative axis descriptions with E5-large-v2 text embeddings, converts them into TF-IDF-like vectors via a word-level codebook, then applies UMAP dimensionality reduction and agglomerative clustering (k=10) to form an “analytical space.”
The authors report strong clustering quality metrics (composite score 0.825, silhouette 0.803, and Calinski–Harabasz 11,196) and use non-negative matrix factorization to derive ten latent thematic topics.
A neighbor-cluster entropy measure is used to identify “boundary institutions” that connect multiple thematic communities, highlighting cross-disciplinary bridging roles.
An interactive React-based web visualization tool lets stakeholders explore similarities, topic profiles, and cross-cluster connections, with example clusters spanning art-science, innovation/industry, academic communities, and electronic music/media.

Abstract

The global landscape of art-technology institutions, including festivals, biennials, research labs, conferences, and hybrid organizations, has grown increasingly diverse, yet systematic frameworks for analyzing their multidimensional characteristics remain scarce. This paper proposes ARTLAS, a computational methodology combining an eight-axis conceptual framework (Curatorial Philosophy, Territorial Relation, Knowledge Production Mode, Institutional Genealogy, Temporal Orientation, Ecosystem Function, Audience Relation, and Disciplinary Positioning) with a text-embedding and clustering pipeline to map 78 cultural-technology institutions into a unified analytical space. Each institution is characterized through qualitative descriptions along the eight axes, encoded via E5-large-v2 sentence embeddings and quantized through a word-level codebook into TF-IDF feature vectors. Dimensionality reduction using UMAP, followed by agglomerative clustering (Average linkage, k=10), yields a composite score of 0.825, a silhouette coefficient of 0.803, and a Calinski-Harabasz index of 11,196. Non-negative matrix factorization extracts ten latent topics, and a neighbor-cluster entropy measure identifies boundary institutions bridging multiple thematic communities. An interactive web-based visualization tool built with React enables stakeholders to explore institutional similarities, thematic profiles, and cross-disciplinary connections. The results reveal coherent groupings such as an art-science hub cluster anchored by ZKM and ArtScience Museum, an innovation and industry cluster including Ars Electronica, transmediale, and Sonar, an ACM academic community cluster comprising TEI, DIS, and NIME, and an electronic music and media cluster including CTM Festival, MUTEK, and Sonic Acts. This work contributes a replicable, data-driven approach to institutional ecology in the cultural-technology sector.