ARTLAS: Mapping Art-Technology Institutions via Conceptual Axes, Text Embeddings, and Unsupervised Clustering
📰 ArXiv cs.AI
ARTLAS is a computational methodology for mapping art-technology institutions using conceptual axes, text embeddings, and unsupervised clustering
Action Steps
- Define the conceptual axes for analyzing art-technology institutions
- Apply text embeddings to represent institutional characteristics
- Use unsupervised clustering to group similar institutions
- Visualize and interpret the results to identify patterns and trends
Who Needs to Know This
Researchers and data scientists on a team can benefit from ARTLAS to analyze and understand the complex landscape of art-technology institutions, while curators and art directors can use it to identify potential partners and collaborations
Key Insight
💡 ARTLAS provides a systematic framework for analyzing the multidimensional characteristics of art-technology institutions
Share This
📈 Map art-tech institutions with ARTLAS: a computational methodology using conceptual axes, text embeddings & clustering
DeepCamp AI