• Knowledge Management Research
• /
• v.25 no.2
• /
• pp.19-47
• /
• 2024

Organizational ability to analyze and utilize data plays an important role in knowledge management and decision-making. This study aims to investigate the potential application of large language models in corporate data analysis. Focusing on the field of human resources, the research examines the data analysis capabilities of these models. Using the widely studied IBM HR dataset, the study reproduces machine learning-based employee turnover prediction analyses from previous research through ChatGPT and compares its predictive performance. Unlike past research methods that required advanced programming skills, ChatGPT-based machine learning data analysis, conducted through the analyst's natural language requests, offers the advantages of being much easier and faster. Moreover, its prediction accuracy was found to be competitive compared to previous studies. This suggests that large language models could serve as effective and practical alternatives in the field of corporate data analysis, which has traditionally demanded advanced programming capabilities. Furthermore, this approach is expected to contribute to the popularization of data analysis and the spread of data-driven decision-making (DDDM). The prompts used during the data analysis process and the program code generated by ChatGPT are also included in the appendix for verification, providing a foundation for future data analysis research using large language models.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.148-155
• /
• 2024

Despite the increasing importance of irony and sarcasm detection in the field of natural language processing, research on the Korean language is relatively scarce compared to other languages. This study aims to experiment with various models for irony detection in Korean text. The study conducted irony detection experiments using KoBERT, a BERT-based model, and ChatGPT. For KoBERT, two methods of additional training on sentiment data were applied (Transfer Learning and MultiTask Learning). Additionally, for ChatGPT, the Few-Shot Learning technique was applied by increasing the number of example sentences entered as prompts. The results of the experiments showed that the Transfer Learning and MultiTask Learning models, which were trained with additional sentiment data, outperformed the baseline model without additional sentiment data. On the other hand, ChatGPT exhibited significantly lower performance compared to KoBERT, and increasing the number of example sentences did not lead to a noticeable improvement in performance. In conclusion, this study suggests that a model based on KoBERT is more suitable for irony detection than ChatGPT, and it highlights the potential contribution of additional training on sentiment data to improve irony detection performance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.3-4
• /
• 2023

자연어처리는 수많은 정보가 수집된 전자의무기록의 비정형 데이터에서 유의미한 정보나 패턴 등을 추출해 의료진의 의사결정을 지원하고, 환자에게 더 나은 진단이나 치료 등을 지원할 수 있어 큰 잠재력을 가지고 있다. 그러나 전자의무기록은 개인정보와 같은 민감한 정보가 다수 포함되어 있어 접근하기 어렵고, 이로 인해 충분한 양의 데이터를 확보하기 어렵다. 따라서 본 논문에서는 신뢰할 수 있는 의료 합성 텍스트를 생성하기 위해 ChatGPT 기반 의료 텍스트 증강 도구를 개발하였다. 이는 사용자가 입력한 실제 의료 텍스트로 의료 합성 데이터를 생성한다. 이를 위해, 적합한 프롬프트와 의료 텍스트에 대한 전처리 방법을 탐색하였다. ChatGPT 기반 의료 텍스트 증강 도구는 입력 텍스트의 핵심 키워드를 잘 유지하였고, 사실에 기반한 의료 합성 텍스트를 생성할 수 있다는 것을 확인할 수 있었다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.191-197
• /
• 2023

The farming diary has significant value for farmers as it serves as crucial documentation, supporting evidence for eco-friendly and GAP (Good Agricultural Practices) certifications, as well as when applying for diverse subsidies. A detailed farming diary holds immense value, yet many farmers face challenges in document preparation, so even though training is provided on how to write a farming diary, making these remains impracticable for some. Therefore, this paper suggests using ChatGPT as a solution, enabling the effortless addition of comprehensive information to existing farming diary. With this method, it is expected that enhancing the thoroughness of the farming diary will significantly amplify its worth as robust certification evidence, thereby providing substantial support for future farming endeavors.

• Communications of Mathematical Education
• /
• v.38 no.1
• /
• pp.49-67
• /
• 2024

Recent interest in the diverse applications of artificial intelligence (AI) language models has highlighted the need to explore didactical uses in mathematics education. AI language models, capable of natural language processing, show promise in solving mathematical word problems. This study tested the capability of ChatGPT, an AI language model, to solve word problems from elementary school textbooks, and analyzed both the solutions and errors made. The results showed that the AI language model achieved an accuracy rate of 81.08%, with errors in problem comprehension, equation formulation, and calculation. Based on this analysis of solution processes and error types, the study suggests implications for the didactical application of AI language models in education.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.189-194
• /
• 2024

Identifying customer needs and improving products and services accordingly is essential for survival and growth in modern business. It's important to do this successfully because it's directly related to increasing customer satisfaction and making the products more competitive. However, user reviews are characterized by unstructured data, which requires various stages of processing for analysis. Due to the need for specialized knowledge and skills to analyze reviews and apply appropriate solutions, small business owners often find it challenging to quickly adopt and reflect customer needs. Therefore, this paper proposes a method that utilizes ChatGPT to identify important and new words in user reviews to derive new customer needs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.74-75
• /
• 2023

본 논문에서는 Chat GPT API 를 활용하여 웹 대시보드를 기획하는 것을 다루고 있다. 이 대시보드는 개인과 업무에서 생성된 데이터를 통합하여 데이터 분석을 쉽게 할 수 있도록 도와주며, 머신 러닝 절차를 기반으로 화면 구성이 이루어졌다. 이를 통해 비전문가도 쉽게 데이터 전처리, 시각화, 학습, 저장소 등의 기능을 사용할 수 있다.

• Annals of Occupational and Environmental Medicine
• /
• v.35
• /
• pp.42.1-42.4
• /
• 2023

ChatGPT has the potential to revolutionize occupational medicine by providing a powerful tool for analyzing data, improving communication, and increasing efficiency. It can help identify patterns and trends in workplace health and safety, act as a virtual assistant for workers, employers, and occupational health professionals, and automate certain tasks. However, caution is required due to ethical concerns, the need to maintain confidentiality, and the risk of inconsistent or inaccurate results. ChatGPT cannot replace the crucial role of the occupational health professional in the medical surveillance of workers and the analysis of data on workers' health.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.667-669
• /
• 2023

데이터의 균형은 객체 인식 분야에서 영향을 미치는 요인 중 하나이다. 본 논문에서는 폐기물 데이터 균형을 위해 Chat-GPT와 Diffusion model 기반 데이터 생성 모델을 제안한다. Chat-GPT를 사용하여 폐기물의 속성에 해당하는 단어를 생성하도록 질문하고, 생성된 단어는 인코더를 통해 벡터화시킨다. 이 중 폐기물과 관련 없는 단어를 삭제 후, 남은 단어들을 결합하는 전처리 과정을 거친다. 결합한 벡터는 디코더를 통해 텍스트 데이터로 변환 후, Stable Diffusion model에 입력되어 텍스트와 상응하는 폐기물 데이터를 생성한다. 이 데이터는 AI Hub의 공공 데이터를 활용하며, 객체 인식 모델인 YOLOv5로 학습해 F1-score와 mAP로 평가한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.399-400
• /
• 2023

본 프로젝트는 ChatGPT와 카카오톡 채널 챗봇을 사용하여 초등학생 대상의 학교폭력 예방교육을 위한 대화형 챗봇을 개발한다. 이를 위해, 한림대학교 간호대학에서 제공받은 학교폭력 예방교육 자료를 기반으로 ChatGPT를 사용하여 데이터를 증강하였고, AWS RDS의 데이터베이스에 사용자의 예상 발화와 그에 대한 답변을 저장하였다. 그리고 AWS Lambda에 REST API를 구현하고, AWS API Gateway를 통해 카카오톡 채널 챗봇과 연결하였다. 사용자가 발화를 입력하면 발화를 포함한 요청이 AWS Lambda로 전달되고, ChatGPT를 사용해 답변을 생성하며 데이터베이스에 저장된 데이터와 코사인 유사도를 비교한다. 이때 기준치보다 유사도가 높다면 저장되어 있던 데이터를 반환하고, 낮다면 생성된 답변을 반환한다. 이후 반환된 답변을 카카오톡 채널 챗봇으로 전달해 사용자에게 출력한다.