한국도서관정보학회지 (Journal of Korean Library and Information Science Society)

한국도서관정보학회 (Korean Library and Information Science Society)
권호 표지
DOI QR코드

DOI QR Code

AttentionMesh를 활용한 국가과학기술표준분류체계 소분류 키워드 자동추천에 관한 연구

A Study on Automatic Recommendation of Keywords for Sub-Classification of National Science and Technology Standard Classification System Using AttentionMesh

  • 박진호 (한성대학교 크리에이티브 인문학부 도서관정보문화트랙) ;
  • 송민선 (대림대학교 도서관미디어정보과)
  • 투고 : 2022.05.25
  • 심사 : 2022.06.21
  • 발행 : 2022.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

이 연구의 목적은 국가과학기술표준분류체계의 소분류 용어를 기계학습 알고리즘을 적용하여 기술키워드 변환하는 것이 목적이다. 이를 위해 본 연구에서는 주제어 추천에 적합한 학습 알고리즘으로 AttentionMeSH를 활용했다. 원천데이터는 한국과학기술기획평가원이 정제한 2017년부터 2020년까지 4개년 연구현황 파일을 사용하였다. 학습은 과제명, 연구목표, 연구내용, 기대효과와 같이 연구내용을 잘 표현하고 있는 4개 속성을 사용했다. 그 결과 임계치(threshold)가 0.5일 때 MiF 0.6377이라는 결과가 도출됨을 확인하였다. 향후 실제 업무에 기계학습을 활용하고, 기술키워드 확보를 위해서는 용어관리체계 구축과 다양한 속성들의 데이터 확보가 필요할 것으로 보인다.

The purpose of this study is to transform the sub-categorization terms of the National Science and Technology Standards Classification System into technical keywords by applying a machine learning algorithm. For this purpose, AttentionMeSH was used as a learning algorithm suitable for topic word recommendation. For source data, four-year research status files from 2017 to 2020, refined by the Korea Institute of Science and Technology Planning and Evaluation, were used. For learning, four attributes that well express the research content were used: task name, research goal, research abstract, and expected effect. As a result, it was confirmed that the result of MiF 0.6377 was derived when the threshold was 0.5. In order to utilize machine learning in actual work in the future and to secure technical keywords, it is expected that it will be necessary to establish a term management system and secure data of various attributes.

키워드

참고문헌

  1. Cho, Hyun Yang (2017). A experimental study on the development of a book recommendation system using automatic classification, based on the personality type. Journal of Korean Library and Information Science Society, 48(2), 215-236. https://doi.org/10.16981/kliss.48.201706.215
  2. Cho, Hyun Yang (2020). Design of the curation platform for user-participated book recommendation system of selecting on alternative material for the disabled. Journal of the Korean Society for Library and Information Science, 54(3), 41-69. https://doi.org/10.4275/KSLIS.2020.54.3.041
  3. Choi, Jong-Yun, Hahn, Hyuk, & Jung, Yu Chul (2020). Research on text classification of research reports using Korea national science and technology standards classification codes. Journal of the Korea Academia-Industrial Cooperation Society, 21(1), 169-177. http://10.5762/KAIS.2020.21.1.169
  4. Han, Hee-Jun, Choi, Yunsoo, & Choi, Sung-Pil (2018). A study on personalization of science and technology information by user interest tracking technique. Journal of the Korean Society for Library and Information Science, 52(3), 5-33. http://10.4275/KSLIS.2018.52.3.005
  5. Kim, Hae Chan Sol, Ahn, Dae Jin, Yim, Jin Hee, & Rieh, Hae-Young (2017). A study on automatic classification of record text using machine learning. Journal of the Korean Society for Information Management, 34(4), 321-344. https://doi.org/10.3743/KOSIM.2017.34.4.321
  6. Kim, Kwang-Young & Kwak, Seung-Jin (2010). A study of personalized retrieval system through society of Korean journal articles of science and technology. Journal of Korean Library and Information Science Society, 41(1), 149-165. http://10.16981/kliss.41.1.201003.149
  7. Kim, Kwang-Young & Kwak, Seung-Jin (2011). A study on personalized search system based on subject classification. Journal of the Korean Society for Library and Information Science, 45(4), 77-102. http://dx.doi.org/10.4275/KSLIS.2011.45.4.077
  8. Kim, Sunghee & Eom, Jae-Eun (2008). A study on the documents's automatic classification using machine learning. Journal of Information Management, 39(4), 47-66. https://doi.org/10.1633/JIM.2008.39.4.047
  9. Kim, Yunjeong, Shin, Donggu, & Jung, Hoikyung (2021). Recommendation system for research field of R&D project using machine learning. Journal of the Korea Institute of Information and Communication Engineering, 25(12), 1809-1816. http://doi.org/10.6109/jkiice.2021.25.12.1809
  10. Korea Institute of S&T Evaluation and Planning (2019). A Study on Reestablishing the Role of KISTEP for Predicting the Future to Enhance the Utilization of Science and Technology Planning and Innovation Policy. Chung-cheong bukdo: Korea Institute of S&T Evaluation and Planning.
  11. Lee, Soyoung & Chung, Young-Mee (2006). Design and evaluation of a personalized search service model based on web portal user activities. Journal of the Korean Society for Information Management, 23(4), 179-196. http://doi.org/10.3743/KOSIM.2006.23.4.179
  12. Ministry of Science and Technology Information and Communication (2019). Selection Results (Draft) for the Revision Feasibility Evaluation of the National Science and Technology Standards Classification System and the Long-term Improvement Direction. Ministry of Science and ICT, Performance Evaluation Policy Bureau, Science and Technology Information Division.
  13. Noh, Young-Hee (2001). The study on the effective automatic classification of internet document using the machine learning. Journal of Korean Library and Information Science Society, 32(3), 307-330.
  14. Song, Min Sun & Park, Jin Ho (2021). A study on development of SKOS-based metadata elements for managing keywords in the national science and technology standard classification system. Journal of the Korean Biblia Society for Library and Information Science, 32(4), 67-88. https://doi.org/10.14699/kbiblia.2021.32.4.067
  15. BioAsQ [n.d.]. Challenges - Tasks 6a, 6b - Year 6. Available: http://bioasq.org/participate/challenges_year_6
  16. BioASQ (n.d.). Sixth Challenge Winners. Available: http://bioasq.org/participate/sixth-challenge-winners
  17. Jin, Q., Dhingra, B., Cohen, W., & Lu, X. (2018). Attentionmesh: simple, effective and interpretable automatic mesh indexer. Proceedings of the 6th BioASQ Workshop a Challenge on Large-scale Biomedical Semantic Indexing and Question Answering, 47-59. https://doi.org/10.18653/v1/W18-5306