Journal of the Korean Society for information Management (정보관리학회지)

Korean Society for Information Management (한국정보관리학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of Performance Factors for Automatic Classification of Records Utilizing Metadata

메타데이터를 활용한 기록물 자동분류 성능 요소 비교

  • 김영범 (전남대학교 대학원 기록관리학) ;
  • 장우권 (전남대학교 문헌정보학과)
  • Received : 2023.08.16
  • Accepted : 2023.09.12
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The objective of this study is to identify performance factors in the automatic classification of records by utilizing metadata that contains the contextual information of records. For this study, we collected 97,064 records of original textual information from Korean central administrative agencies in 2022. Various classification algorithms, data selection methods, and feature extraction techniques are applied and compared with the intent to discern the optimal performance-inducing technique. The study results demonstrated that among classification algorithms, Random Forest displayed higher performance, and among feature extraction techniques, the TF method proved to be the most effective. The minimum data quantity of unit tasks had a minimal influence on performance, and the addition of features positively affected performance, while their removal had a discernible negative impact.

이 연구의 목적은 기록물의 맥락정보를 담고 있는 메타데이터를 활용하여 기록물 자동분류 과정에서의 성능요소를 파악하는데 있다. 연구를 위해 2022년 중앙행정기관 원문정보 약 97,064건을 수집하였다.수집한 데이터를 대상으로 다양한 분류 알고리즘과 데이터선정방법, 문헌표현기법을 적용하고 그 결과를 비교하여 기록물 자동 분류를 위한 최적의 성능요소를 파악하고자 하였다. 연구 결과 분류 알고리즘으로는 Random Forest가, 문헌표현기법으로는 TF 기법이 가장 높은 성능을 보였으며, 단위과제의 최소데이터 수량은 성능에 미치는 영향이 미미하였고 자질은 성능변화에 명확한 영향을 미친다는 것이 확인되었다.

Keywords

References

  1. Bang, Jae Hyun (2018). A Study on Application of Machine Learning for Intelligent Archive System: Focusing on Application of Deep Neural Network. Doctoral dissertation, Hankuk University of Foreign Studies. 
  2. Choi, Yunsoo & Choi, Sung-Pil (2019), A study on patent literature classification using distributed representation of technical terms. Journal of the Korean Society for Library and Information Science, 53(2), 179-199. https://doi.org/10.4275/KSLIS.2019.53.2.179 
  3. Enforcement Decree of Records Management of Public Institution Act. No.16609. 
  4. Enforcement Decree of the Public Records Management Act. No.19985. 
  5. Jang, Ji-Sook & Rieh, Hae-Young (2009). Design of automatic records classification system using contextual information. Journal of Korean Society of Archives and Records Management, 9(1), 151-173. https://doi.org/10.14404/JKSARM.2009.9.1.151 
  6. Jeong, Jihye, Lee, Gemma, Wang, Hosung, & Oh, Hyo-Jung (2022). Building the outlier candidate discrimination training data based on inventory for automatic classification of transferred records. Journal of Korean Society of Archives and Records Management, 22(1), 43-59. https://doi.org/10.14404/JKSARM.2022.22.1.043 
  7. Kim, Hae Chan Sol, Ahn, Dae Jin, Lim, Jin Hee, & Lee, Haeyoung (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. 
  8. Kim, Pan Jun (2016). An analytical study on performance factors of automatic classification based on machine learning. Journal of the Korean Society for Information Management, 33(2), 33-59. https://doi.org/10.3743/KOSIM.2016.33.2.033 
  9. Kim, Pan Jun (2019). An analytical study on automatic classification of domestic journal articles using random forest. Journal of the Korean Society for Information Management, 36(2), 57-77. https://doi.org/10.3743/KOSIM.2019.36.2.057 
  10. Kim, Suyeon, Ahn, Seokho, Kim, Donghyun, Lee, Euijong, & Seo, Young-Duk (2022), Accuracy analysis by part-of-speech of morpheme analyzers. Proceedings of Korean Istitute of Information Technology Conference, 378-381. 
  11. Lee, Hyunsil & Han, SungKook (2006). Conceptual modeling of record management metadata. Journal of the Korean Society for Information Management, 23(3), 23-48. https://doi.org/10.3743/KOSIM.2006.23.3.023 
  12. Lee, Wonyoung (2000). The principles of records classification: compares with librarian materials. The Korean Journal of Archival Studies, 2, 103-128. https://doi.org/10.20923/kjas.2000.2.103 
  13. Nam, Eunkyung, Ahn, Hye-Rim, & Song, Min (2013). Automatic classification system for record management of bulletin board on public website. Proceedings of the 20th Academic Conference of the Korean Society for Information Management, 175-178. 
  14. National Archives of Korea (2012). Guide for Determining the Retention Period of University Records(11-1311153-000250-01). 
  15. National Archives of Korea (2017). A Study on Designing a Next-Generation Records Management Model(11-1741050-000008-01). 
  16. National Archives of Korea (2021). Study on Common Training Dataset Construction for Appling AI Technology for Records Managements(11-1741050-000073-01). 
  17. Records Management of Public Institution Act. No. 5709. 
  18. Regulations on the Classification and Management of Government Functions. Presidential Decree No. 209. 
  19. Seol, Mun Won (2012). Research trends and issues of records and archives classification in Korea. Journal of the Korean Society for Archives and Records Management, 12(3), 203-232. 
  20. Seol, Mun Won (2013). A study on problems of the public records appraisal system based on the value of 'business transaction' and application of a multi-appraisal model. Journal of the Korean Society for Archives and Records Management, 13(3), 231-254. https://doi.org/10.14404/JKSARM.2013.13.3.231. 
  21. Yuk, JeeHee & Song, Min (2018). A study of research on methods of automated biomedical document classification using topic modeling and deep learning. Journal of the Korean Society for Information Management, 35(2), 63-88. https://doi.org/10.3743/KOSIM.2018.35.2.063 
  22. Gates, W. H (2023. March 21). The Age of AI has begun. Available: https://www.gatesnotes.com/The-Age-of-AI-Has-Begun 
  23. Jo, T. & Japkowicz, N. (2004). Class imbalances versus small disjuncts. Association for Computing Machinery Special Interest Group on Knowledge Discovery in Data Exploration, 6, 40-49. https://doi.org/10.1145/1007730.1007737