Identifying patterns in rare earth element patents based on text and data mining

Yonghan Ju, So Young Sohn

Research output: Contribution to journalArticlepeer-review

22 Citations (Scopus)


Rare earth elements (REE) are needed to produce many cutting-edge products, and their depletion is a major concern. In this paper, we identify unique characteristics of REE-related patents granted from 1975 to 2013 in five large patent offices around the world. Through topic detection and clustering of patent text, we found that purification processes related to oxides, nitrogen oxide, and exhaust gas were highlighted in the Korean Intellectual Property Office and Japan Patent Office (JPO). Molecular sieve, dispersion, and preparation methods involving yttrium, cerium, methane, zirconium, and ammonia were prominent in the China Patent and Trademark Office (CPTO) in the areas of performing operation and transporting. Quadratic assignment procedure correlation analysis was performed for IPC co-occurrence among REE patents in different offices, and the United States Patent and Trademark Office showed significantly different patterns than the CPTO and JPO. Furthermore, using betweenness centrality as an indicator of technology transition, the manufacture and treatment of nanostructures, nanotechnology for materials and surface science, and electrodes were identified as important REE technologies to be protected in Korea. In Japan, the technological areas identified as important for protection were the apparatuses and processes of manufacturing or assembling devices, compounds of iron, and materials. Our study results offer insights into national strategies for REE-related technologies in each country.

Original languageEnglish
Pages (from-to)389-410
Number of pages22
Issue number1
Publication statusPublished - 2015 Jan

Bibliographical note

Publisher Copyright:
© Akadémiai Kiadó, Budapest, Hungary 2014

All Science Journal Classification (ASJC) codes

  • Social Sciences(all)
  • Computer Science Applications
  • Library and Information Sciences


Dive into the research topics of 'Identifying patterns in rare earth element patents based on text and data mining'. Together they form a unique fingerprint.

Cite this