@article{ART003318145},
author={Sein Min and Eungi Kim},
title={LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type},
journal={Journal of Korean Library and Information Science Society},
issn={2466-2542},
year={2026},
volume={57},
number={1},
pages={413-438},
doi={10.16981/kliss.57.1.202603.413}
TY - JOUR
AU - Sein Min
AU - Eungi Kim
TI - LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type
JO - Journal of Korean Library and Information Science Society
PY - 2026
VL - 57
IS - 1
PB - Korean Library And Information Science Society
SP - 413
EP - 438
SN - 2466-2542
AB - The purpose of this study is to compare and examine, across multiple dimensions, the conditions under which large language model (LLM)-based content analysis can be applied according to task type in the context of research methods analysis in library and information science. To this end, 100 survey and interview studies published between 2020 and 2024 in four major Korean journals in library and information science were selected using stratified random sampling. The coding results produced by one human coder and four large language models (Claude-3.5-Haiku, GPT-4o-Mini, Gemini-2.0-Flash, and Grok-4-Latest) were compared across twelve dimensions constituting sampling methodology. The results show that relatively high levels of agreement were observed in dimensions where classification could be made based on explicit criteria, whereas consistently lower levels of agreement appeared in dimensions requiring inferential or evaluative judgment. These findings suggest that the performance of LLM-based automated coding is influenced more by the decision structure of the task and the explicitness of the available information than by model performance itself. Therefore, the scope of LLM application should be more carefully examined from the perspectives of task type and judgment characteristics, and the systematic design of human-AI hybrid validation strategies is required.
KW - Large Language Models;Automated Content Analysis;Coding Reliability;Library and Information Science Research Methods;Sampling Methodology
DO - 10.16981/kliss.57.1.202603.413
ER -
Sein Min and Eungi Kim. (2026). LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type. Journal of Korean Library and Information Science Society, 57(1), 413-438.
Sein Min and Eungi Kim. 2026, "LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type", Journal of Korean Library and Information Science Society, vol.57, no.1 pp.413-438. Available from: doi:10.16981/kliss.57.1.202603.413
Sein Min, Eungi Kim "LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type" Journal of Korean Library and Information Science Society 57.1 pp.413-438 (2026) : 413.
Sein Min, Eungi Kim. LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type. 2026; 57(1), 413-438. Available from: doi:10.16981/kliss.57.1.202603.413
Sein Min and Eungi Kim. "LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type" Journal of Korean Library and Information Science Society 57, no.1 (2026) : 413-438.doi: 10.16981/kliss.57.1.202603.413
Sein Min; Eungi Kim. LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type. Journal of Korean Library and Information Science Society, 57(1), 413-438. doi: 10.16981/kliss.57.1.202603.413
Sein Min; Eungi Kim. LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type. Journal of Korean Library and Information Science Society. 2026; 57(1) 413-438. doi: 10.16981/kliss.57.1.202603.413
Sein Min, Eungi Kim. LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type. 2026; 57(1), 413-438. Available from: doi:10.16981/kliss.57.1.202603.413
Sein Min and Eungi Kim. "LLM-Based Content Analysis of Sampling Methodology in Library and Information Science Research: A Cross-Model Comparison of Coding Performance by Task Type" Journal of Korean Library and Information Science Society 57, no.1 (2026) : 413-438.doi: 10.16981/kliss.57.1.202603.413
