[S3] S3 Digital Transformation Initiative R&D for Magnetic Materials III(1)

4:10 PM - 4:25 PM JST(7:10 AM - 7:25 AM UTC)

[S3.9] Global Metadata Clustering from Ultra-large-scale Soft Magnetic Material using Large Language Model

○ruixuan Ying¹, Yunhao Liang², Takuya Taniguchi¹, Satoshi Okamoto¹ (1. Tohoku Univ., 2. Chinese Academy of Sciences)

Keywords:

Soft Magnetic Materials,Large-scale Metadata Analysis,Large Language Models,Unsupervised Clustering,Research Landscape Mapping

This study builds an ultra-large metadata database of 750,000 abstracts on soft magnetic materials. Using large language model embeddings with UMAP and HDBSCAN, it maps the global research landscape, automatically revealing major themes and emerging frontiers.