• Journal of the Korean Society for Library and Information Science
• /
• v.57 no.2
• /
• pp.349-377
• /
• 2023

With the recent advancements in artificial intelligence, the emergence of ChatGPT is expected to bring significant changes to various industries. In particular, there are active attempts to introduce ChatGPT in the education sector, and for librarians, utilizing ChatGPT is seen as an essential element for future learning tools. Against this background, this study aimed to examine librarians' perceptions of introducing ChatGPT in the school library through Focus Group Interviews (FGI). As a result, six themes were derived, including differences in perceptions of ChatGPT application in school libraries, teaching and learning activities utilizing ChatGPT, practical operation of ChatGPT, considerations for successful performance, librarians' required competencies and environment (infrastructure), and the development direction of ChatGPT utilization services in school libraries. Based on these findings, implications for the necessity of educational services utilizing ChatGPT were proposed. This study is significant as the first attempt to introduce ChatGPT in the school library field.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.139-151
• /
• 2023

This study aims to gain insights into ChatGPT, which has recently received significant attention. The study utilized a mixed method involving case studies and news big data analysis. ChatGPT can be described as an optimized language model for dialogue. The question arises whether ChatGPT will replace Google search services, posing a potential threat to Google. It could hurt Google's advertising business, which is the foundation of its profits. With AI-based chatbots like ChatGPT likely to disrupt the web search industry, Google is establishing a new AI strategy. The study used the BIG KINDS service and analyzed 2,136 articles over six months, from August 23, 2022, to February 22, 2023. Thirty of these articles were written in 2022, while 2,106 have been reported recently as of February 22, 2023. Also, the study examined the contents of ChatGPT by utilizing literature research, news big data analysis, and use cases. Despite limitations such as the potential for false information, analyzing news big data and use cases suggests that ChatGPT is worth using.

• Environmental Analysis Health and Toxicology
• /
• v.17 no.3
• /
• pp.239-243
• /
• 2002

Changes of plasma vitellogenin (VTG) and glutamate pyruvate transaminase (GPT) were examined for determining whether hepatocyte was damaged during the process of VTG induction in the juvenile rockfish, Sebastes schlegeli exposed to exogenous estrogen (estradiol-l7$\beta$, E$_2$). Rockfishes were intraperitoneally injected with E$_2$(5 mg/kg B.W.) in 70% ethanol and plasma sampling were extracted at 0, 1, 3, 6, 9, 12, 15 days af-ter E$_2$administration. VTG and GPT were then analyzed by SDS -PAGE and Reitman -Frankel method, respectively. VTG band was detected at a molecular weight position of 175 kDa on Day 3 after E$_2$administration. This band became more distinct at 6 days, but its was gradually thinned with time -course, and not detected at 15 days. GPT was suddenly increased at 1 days after 22 administration and highest GPT was detected at 3 days. However. GPT was gradually decreased with time -course as the change of VTG. These results suggest that the process of VTG induction by exogenous E$_2$damage to hepatocyte, and plasma GPT was temporarily increased in the juvenile rockfish.

• Journal of fish pathology
• /
• v.17 no.3
• /
• pp.191-198
• /
• 2004

Temporal changes of plasma vitellogenin (VTG), alkaline-labile protein phosphorus (ALPP), calcium (Ca), glutamate pyruvate transaminase (GPT) and hepatosomatic index (HSI) were examined in the $estradiol-17\beta$ ${E_2}$-administered immature rockfish, Sebastes schlegeli. Fish were intraperitoneally injected with ${E_2}$ (5 ㎎/kg B.W.) in 70% ethanol and then plasma were extracted at 0, 1, 3, 6, 9, 12 and 15 days. VTG band was detected at a molecular weight position of about 170 kDa on Day 3 in SDS-PAGE. This band became more distinct at 6 days but its was gradually thinned with time-course, and not detected at 15 days. Plasma ALPP and Ca increased suddenly at 1 day and the highest concentrations were detected at 6 days and then these concentrations decreased gradually with time-course. ALPP and Ca concentrations at 15 days after E2 administration were very similar to that before E2 administration. GPT was increased at 1 day and higher GPT was detected at 3 days. However, GPT was gradually decreased with time-course. GPT and HSI at 15 days after E2 administration were also very similar to that before E2 administration. HSI was also increased at 1 day and the highest value was detected at 3 days and then gradually decreased with time-course. These results suggest that plasma ALPP, Ca, GPT and HSI could be utilized as a biomarker of exogenous E2 exposure in coastal ecosystem, because the changes of ALPP, Ca, GPT and HSI after E2 administration are very similar to that of VTG.

• Education of Primary School Mathematics
• /
• v.26 no.2
• /
• pp.99-113
• /
• 2023

In this study, I explored the possibility of using ChatGPT math education. For this purpose, students' problem-solving outputs and conversation data between pre-service teachers and a student were selected as an analysis case. A case was analyzed using ChatGPT and compared with the results of mathematics education experts. The results that ChatGPT analyzed students' problem-solving strategies and mathematical thinking skills were similar to those of math education experts. ChatGPT was able to analyze teacher questions with evaluation criteria, and the results were similar to those of math education experts. ChatGPT could also respond with mathematical theory as a source of evaluation criteria. These results demonstrate the potential of ChatGPT to analyze students' thinking and teachers' practice in mathematics education. However, there are limitations in properly applying the evaluation criteria or providing inaccurate information, so the further review of the derived information is required.

• Communications of Mathematical Education
• /
• v.37 no.2
• /
• pp.233-256
• /
• 2023

This study conducted foundational research to derive ways to use ChatGPT in mathematics education by analyzing ChatGPT's responses to questions from the National Assessment of Educational Achievement (NAEA) and the College Scholastic Ability Test (CSAT). ChatGPT, a generative artificial intelligence model, has gained attention in various fields, and there is a growing demand for its use in education as the number of users rapidly increases. To the best of our knowledge, there are very few reported cases of educational studies utilizing ChatGPT. In this study, we analyzed ChatGPT 3.5 responses to questions from the three-year National Assessment of Educational Achievement and the College Scholastic Ability Test, categorizing them based on the percentage of correct answers, the accuracy of the solution process, and types of errors. The correct answer rates for ChatGPT in the National Assessment of Educational Achievement and the College Scholastic Ability Test questions were 37.1% and 15.97%, respectively. The accuracy of ChatGPT's solution process was calculated as 3.44 for the National Assessment of Educational Achievement and 2.49 for the College Scholastic Ability Test. Errors in solving math problems with ChatGPT were classified into procedural and functional errors. Procedural errors referred to mistakes in connecting expressions to the next step or in calculations, while functional errors were related to how ChatGPT recognized, judged, and outputted text. This analysis suggests that relying solely on the percentage of correct answers should not be the criterion for assessing ChatGPT's mathematical performance, but rather a combination of the accuracy of the solution process and types of errors should be considered.

• Therapeutic Science for Rehabilitation
• /
• v.13 no.1
• /
• pp.65-74
• /
• 2024

Objective : This study assessed ChatGPT, an artificial intelligence system based on a large language model, for its ability to pass the National Korean Occupational Therapy Licensure Examination (NKOTLE). Methods : Using NKOTLE questions from 2018 to 2022, provided by the Korea Health and Medical Personnel Examination Institute, this study employed English prompts to determine the accuracy of ChatGPT in providing correct answers. Two researchers independently conducted the entire process, and the average accuracy of both researchers was used to determine whether ChatGPT passed over the 5-year period. The degree of agreement between ChatGPT answers of the two researchers was assessed. Results : ChatGPT passed the 2020 examination but failed to pass the other 4 years' examination. Specifically, its accuracy in questions related to medical regulations ranged from 25% to 57%, whereas its accuracy in other questions exceeded 60%. ChatGPT exhibited a strong agreement between researchers, except for medical regulation questions, and this agreement was significantly correlated with accuracy. Conclusion : There are still limitations to the application of ChatGPT to answer questions influenced by language or culture. Future studies should explore its potential as an educational tool for students majoring in occupational therapy through optimized prompts and continuous learning from the data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.381-383
• /
• 2022

최근 자연어처리 분야에서는 Bert, GPT 등 Transformer기반의 언어모델 연구가 활발히 이뤄지고 있다. 이러한 언어모델은 대용량의 말뭉치 데이터와 많은 파라미터를 이용하여 사전학습을 진행하여 다양한 자연어처리 테스트에서 높은 성능을 보여주고 있다. 이에 본 논문에서는 Transformer기반의 언어모델인 Bert와 GPT-2의 성능평가를 진행한다. 성능평가는 '네이버 영화 리뷰' 데이터 셋을 통해 긍정 부정의 정확도와 학습시간을 측정한다. 측정결과 정확도에서는 GPT-2가 Bert보다 최소 4.16%에서 최대 5.32% 높은 정확도를 나타내었지만 학습시간에서는 Bert가 GPT-2보다 최소 104초에서 116초 빠르게 나타났다. 향후 성능 비교는 더 많은 데이터와 다양한 조건을 통해 구체적인 성능 비교가 필요하다.

• The Journal of Internal Korean Medicine
• /
• v.30 no.4
• /
• pp.685-695
• /
• 2009

Objectives : In this study, the author tried to investigate whether Geonpye-tang(GPT) significantly affects PMA-, EGF- or TNF-alpha-induced MUC5AC mucin production and gene expression from human airway epithelial cells. Materials and Methods : Effects of the agent on PMA-, EGF- or TNF-alpha-induced MUC5AC mucin production and gene expression from human airway epithelial cells (NCI-H292) were investigated. Confluent NCI-H292 cells were pretreated for 30 min in the presence of GPT and treated with PMA (10ng/ml) or EGF (25ng/ml) or TNF-alpha (0.2nM), to assess both effect of the agent on PMA- or EGF- or TNF-alpha-induced MUC5AC mucin production by enzyme-linked immunosorbent assay (ELISA) and gene expression by reverse transcription-polymerase chain reaction (RT-PCR). Possible cytotoxicity of the agent was assessed by examining the rate of survival and proliferation of NCI-H292 cells after treatment with the agent over 72 hrs (SRB assay). Results : (1) GPT significantly inhibited PMA-induced and EGF-induced MUC5AC mucin production from NCI-H292 cells. However, GPT did not affect TNF-alpha-induced MUC5AC mucin production. (2) GPT significantly inhibited the expression levels of PMA-, EGF- or TNF-alpha-induced MUC5AC genes in NCI-H292 cells (3) GPT did not show significant cytotoxicity to NCI-H292 cells. Conclusion : This result suggests that GPT can affect the production and gene expression of respiratory mucin observed in diverse respiratory diseases accompanied by mucus hypersecretion. This can explain the traditional use of GPT in oriental medicine. Effects of GPT with their components should be further investigated using animal experimental models that reflect pathophysiology of airway diseases through future studies.

• Journal of the Korean Society for information Management
• /
• v.40 no.2
• /
• pp.183-209
• /
• 2023

The purpose of this study is to evaluate the Dublin Core metadata generated by ChatGPT using book covers, title pages, and colophons from a collection of books. To achieve this, we collected book covers, title pages, and colophons from 90 books and inputted them into ChatGPT to generate Dublin Core metadata. The performance was evaluated in terms of completeness and accuracy. The overall results showed a satisfactory level of completeness at 0.87 and accuracy at 0.71. Among the individual elements, Title, Creator, Publisher, Date, Identifier, Rights, and Language exhibited higher performance. Subject and Description elements showed relatively lower performance in terms of completeness and accuracy, but it confirmed the generation capability known as the inherent strength of ChatGPT. On the other hand, books in the sections of social sciences and technology of DDC showed slightly lower accuracy in the Contributor element. This was attributed to ChatGPT's attribution extraction errors, omissions in the original bibliographic description contents for metadata, and the language composition of the training data used by ChatGPT.