BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart
Joonhyung Bae
TL;DR
BioArtlas tackles the multidimensionality of bioart by introducing axis-aware representations and a codebook-based clustering framework to fuse thirteen analytical axes while preserving their semantic distinctions. The method employs a two-stage representation: per-axis embeddings aggregated into axis-level vectors, followed by codebook construction via PCA-preprocessed K-means and axis-wise feature activations, enabling cross-dimensional comparisons. A large, systematic sweep over representation spaces and clustering algorithms identifies an interpretable atlas, with the best configuration being Agglomerative clustering on a four-dimensional UMAP with fifteen clusters, yielding a coherent partition and robust neighborhood structure. The results are translated into an interactive web interface and publicly released dataset, providing a reproducible, scalable model for computational cultural analysis of bioart and offering a pathway for future multi-annotator validation and geographic expansion.
Abstract
Bioart's hybrid nature spanning art, science, technology, ethics, and politics defies traditional single-axis categorization. I present BioArtlas, analyzing 81 bioart works across thirteen curated dimensions using novel axis-aware representations that preserve semantic distinctions while enabling cross-dimensional comparison. Our codebook-based approach groups related concepts into unified clusters, addressing polysemy in cultural terminology. Comprehensive evaluation of up to 800 representation-space-algorithm combinations identifies Agglomerative clustering at k=15 on 4D UMAP as optimal (silhouette 0.664 +/- 0.008, trustworthiness/continuity 0.805/0.812). The approach reveals four organizational patterns: artist-specific methodological cohesion, technique-based segmentation, temporal artistic evolution, and trans-temporal conceptual affinities. By separating analytical optimization from public communication, I provide rigorous analysis and accessible exploration through an interactive web interface (https://www.bioartlas.com) with the dataset publicly available (https://github.com/joonhyungbae/BioArtlas).