@article{ART003084948},
author={Minji Kim and Sunghee Kang and Rieh, Hae-Young},
title={A Case Study on Metadata Extraction for Records Management Using ChatGPT},
journal={Journal of Korean Society of Archives and Records Management},
issn={1598-1487},
year={2024},
volume={24},
number={2},
pages={89-112},
doi={10.14404/JKSARM.2024.24.2.089}
TY - JOUR
AU - Minji Kim
AU - Sunghee Kang
AU - Rieh, Hae-Young
TI - A Case Study on Metadata Extraction for Records Management Using ChatGPT
JO - Journal of Korean Society of Archives and Records Management
PY - 2024
VL - 24
IS - 2
PB - Korean Society of Archives and Records Management
SP - 89
EP - 112
SN - 1598-1487
AB - Metadata is a crucial component of record management, playing a vital role in properly managing and understanding the record. In cases where automatic metadata assignment is not feasible, manual input by records professionals becomes necessary. This study aims to alleviate the challenges associated with manual entry by proposing a method that harnesses ChatGPT technology for extracting records management metadata elements. To employ ChatGPT technology, a Python program utilizing the LangChain library was developed. This program was designed to analyze PDF documents and extract metadata from records through questions, both with a locally installed instance of ChatGPT and the ChatGPT online service. Multiple PDF documents were subjected to this process to test the effectiveness of metadata extraction. The results revealed that while using LangChain with ChatGPT-3.5 turbo provided a secure environment, it exhibited some limitations in accurately retrieving metadata elements. Conversely, the ChatGPT-4 online service yielded relatively accurate results despite being unable to handle sensitive documents for security reasons. This exploration underscores the potential of utilizing ChatGPT technology to extract metadata in records management. With advancements in ChatGPT-related technologies, safer and more accurate results are expected to be achieved. Leveraging these advantages can significantly enhance the efficiency and productivity of tasks associated with managing records and metadata in archives.
KW - Metadata;Records Management Metadata;ChatGPT;Langchain;Archival Information Service
DO - 10.14404/JKSARM.2024.24.2.089
ER -
Minji Kim, Sunghee Kang and Rieh, Hae-Young. (2024). A Case Study on Metadata Extraction for Records Management Using ChatGPT. Journal of Korean Society of Archives and Records Management, 24(2), 89-112.
Minji Kim, Sunghee Kang and Rieh, Hae-Young. 2024, "A Case Study on Metadata Extraction for Records Management Using ChatGPT", Journal of Korean Society of Archives and Records Management, vol.24, no.2 pp.89-112. Available from: doi:10.14404/JKSARM.2024.24.2.089
Minji Kim, Sunghee Kang, Rieh, Hae-Young "A Case Study on Metadata Extraction for Records Management Using ChatGPT" Journal of Korean Society of Archives and Records Management 24.2 pp.89-112 (2024) : 89.
Minji Kim, Sunghee Kang, Rieh, Hae-Young. A Case Study on Metadata Extraction for Records Management Using ChatGPT. 2024; 24(2), 89-112. Available from: doi:10.14404/JKSARM.2024.24.2.089
Minji Kim, Sunghee Kang and Rieh, Hae-Young. "A Case Study on Metadata Extraction for Records Management Using ChatGPT" Journal of Korean Society of Archives and Records Management 24, no.2 (2024) : 89-112.doi: 10.14404/JKSARM.2024.24.2.089
Minji Kim; Sunghee Kang; Rieh, Hae-Young. A Case Study on Metadata Extraction for Records Management Using ChatGPT. Journal of Korean Society of Archives and Records Management, 24(2), 89-112. doi: 10.14404/JKSARM.2024.24.2.089
Minji Kim; Sunghee Kang; Rieh, Hae-Young. A Case Study on Metadata Extraction for Records Management Using ChatGPT. Journal of Korean Society of Archives and Records Management. 2024; 24(2) 89-112. doi: 10.14404/JKSARM.2024.24.2.089
Minji Kim, Sunghee Kang, Rieh, Hae-Young. A Case Study on Metadata Extraction for Records Management Using ChatGPT. 2024; 24(2), 89-112. Available from: doi:10.14404/JKSARM.2024.24.2.089
Minji Kim, Sunghee Kang and Rieh, Hae-Young. "A Case Study on Metadata Extraction for Records Management Using ChatGPT" Journal of Korean Society of Archives and Records Management 24, no.2 (2024) : 89-112.doi: 10.14404/JKSARM.2024.24.2.089
