Journal of the Korean Society for Library and Information Science
- P-ISSN1225-598X
- E-ISSN2982-6292
Article Contents
- 2025 (Vol.59)
- 2024 (Vol.58)
- 2023 (Vol.57)
- 2022 (Vol.56)
- 2021 (Vol.55)
- 2020 (Vol.54)
- 2019 (Vol.53)
- 2018 (Vol.52)
- 2017 (Vol.51)
- 2016 (Vol.50)
- 2015 (Vol.49)
- 2014 (Vol.48)
- 2013 (Vol.47)
- 2012 (Vol.46)
- 2011 (Vol.45)
- 2010 (Vol.44)
- 2009 (Vol.43)
- 2008 (Vol.42)
- 2007 (Vol.41)
- 2006 (Vol.40)
- 2005 (Vol.39)
- 2004 (Vol.38)
- 2003 (Vol.37)
- 2002 (Vol.36)
A Study on Analysis and Automatic Classification of Subject Headings in English Translations of Korean Fictions
Young Joon Nam
Abstract
This study analyzes the subject headings of 492 English translations of Korean fictions and evaluates machine learning-based automatic classification models. Bibliographic data were collected from the Digital Library of Korean Literature and WorldCat. Subject heading frequencies and FAST facet distributions were visualized, and key labels were selected for multi-label classification. Among various models, deep learning models using summaries as features showed the highest performance (F1 = 0.62, AUC = 0.89), with AUC values above 0.8 for 9 out of 10 labels. Additionally, based on ROC curves and confusion matrices, the study identified labels with lower performance and explored the relationships between certain labels. This study demonstrates the potential of deep learning models for classifying subjects in translated Korean literature.
- keywords
- Translated Literlature, Korean Fictions, Subject Headings, Multi-label Classification, Automated Subject Classification