earticle

논문검색

ChatGPT 기반 초등학교 6학년 과학교육용 챗봇 개발

원문정보

Development of a ChatGPT-Based Chabot for Science Education in 6th Grade Elementary School

양현아, 김갑수

초록

영어

Along with the social interest in generative artificial intelligence brought about by ChatGPT, attempts are steadily being made to apply it to education. Unlike conventional rule-based chatbots, ChatGPT-based generative chatbots are meaningful in that they can create sentences by newly constructing meanings based on ultra-large AI and present various cases using a large amount of data. This will help students view scientific concepts and cases in various directions and organize knowledge in a form that suits them. In this study, an educational chatbot was developed in which the GPT-3.5 model was Fine-tuned according to the level of sixth graders in elementary school in Korea and the contents of the science curriculum. The GPT-3.5-turbo-16k-0613 model provided by OpenAI was utilized and fine-tuned to suit the purpose. In this process, it was found that not only sufficient datasets should be secured in advance, but the more detailed and detailed the System settings were, the more selected answers were generated according to the developer's intention.

한국어

ChatGPT가 불러온 생성형 인공지능에 대한 사회적 관심과 함께 이를 교육에 적용하기 위한 시도가 꾸준히 이 루어지고 있다. ChatGPT 기반 생성형 챗봇은 기존의 규칙 기반 챗봇과는 달리 초거대 AI를 바탕으로 새롭게 의 미를 구성하여 문장을 생성하고, 대량의 데이터를 활용해 다양한 사례를 제시해줄 수 있다는 것에 의의가 있다. 이는 학생들이 과학 개념 및 사례에 다양한 방향으로 바라보고, 자신에 적합한 형태로 지식을 구성하도록 도움을 줄 것이다. 본 논문에서는 GPT-3.5 모델을 우리나라 초등학교 6학년의 수준과 과학과 교육과정 내용에 맞게 Fine-tuning한 교육용 챗봇을 개발하였다. OpenAI에서 제공하는 GPT-3.5-turbo-16k-0613 모델을 활용했으며 목 적에 맞게 미세조정 했다. 이 과정에서 사전에 충분한 데이터셋을 확보해야 함은 물론 System 설정을 세분화하고 구체적으로 입력할수록 개발자의 의도에 맞게 정선된 답변을 생성하는 것을 알 수 있었다.

목차

요약
Abstract
1. 서론
2. 관련 연구
2.1. 챗봇(Chatbot)
2.2. ChatGPT
2.3. 인공지능 챗봇 관련 국내 연구 동향 및 챗봇활용 현황 분석: 과학교육에서의 활용을 위한 시사점을 중심으로
3. 개발 내용
3.1. 기본 방향
3.2. 챗봇 설계 시 고려사항
3.3. 개발 환경
3.4. Fine-tuning
3.5. 데이터셋
3.6. 예상 결과
3.7. 출력 제어 및 응답 결과
3.8. 프로그램 설계
3.9. 제언
4. 결론
참고문헌

저자정보

  • 양현아 Hyeona Yang. 내양초등학교
  • 김갑수 Kapsu Kim. 서울교육대학교

참고문헌

자료제공 : 네이버학술정보
  • 1Busan Metropolitan Office of Education. (2023). The Busan Metropolitan Office of Education conducts the nation's first artificial intelligence chatbot 'Chat GPT'training, Press, https://www.pen.go.kr/board/vie-w.pen?boardId=BBS_0000025&menuCd=DOM_000000104006001000&dataSid=6012456.
  • 2Ministry of Education. (2021). The main points of the general outline of the 2022 revised curriculum (draft).
  • 3Jang, H. J., & So, H. J. (2023). The Analysis of Research Trends and Topics about the Educational Use of ChatGPT. Journal of Research in Curriculum & Instruction, 27.4, 387-401.
  • 4Park, E. J. (2023). Meta-analysis on the effect of English education programs using AI Chatbots on language education effectiveness. Journal of the Korea English Education Society, 22(3), 113-132.
  • 5Kim. S. K., Shin. M. C., & Kang. J. Y. (2018), Chatbot Technology Introduction and Case Analysis, Journal of The Korean Institute of Communication Sciences 35.2(Annex 8), 21-28.
  • 6Lee, G. L. (2023). University students’ change of awareness and self-directed learning competencies after experience using and applying Chat GPT. Journal of Teaching & Learning research, 16.3, 71-94.
  • 7Kim, M. J., Yeom, J. Y., Jung, H. W., & Lim, C. I. (2021). A Review of Research on Artificial Intelligence Chatbot in Education through the Lens of Activity Theory. Journal of Korean Association for Educational Information and Media, 27.2, 699-721.
  • 8Jovanovic, M., & Campbell, M. (2022). Generative Artificial Intelligence: Trends and Prospects. Computer, 55(10), 107-112.
  • 9Busan Metropolitan Office of Education. (2019). Artificial Intelligence-Based Training Guidebook, 108-109.
  • 10Kim. H. J., Rhee. S. W., Jeong. S. H., & Tahk. H. S. (2020). The Study of Framework of Structural Scenarios for Chatbot Docent in Science Centers and Museums. Journal of the Korea Convergence Society, 11(11), 115-121.
  • 11Chang. J. A., Park. J. H., & Park. J. S. (2021). An analysis on the trends of education research related to ‘Artificial Intelligence chatbot’ in Korea:Focusing on implications for use in science education. The Journal of Learner-Centered Curriculum and Instruction, 21.13, 729-743.
  • 12Kim. D. K. (2020). Google Colab. Magazine of the SAREK, 49.10, 110-111.
  • 13Ministry of education(2015). Ministry of Education Notice No. 2015-74 [Annex 9] [Education Report]Science Department Curriculum, 5-12.
  • 14Joo. H. N. (2023). ChatGPT Developer Handbook, Seoul: Decoding.
  • 15Choi. E. Y. (2020). Data structure for efficient proc-ess of motion infographics using data driven_based on JSON. Cartoon and Animation Studies, 89-110, 10.7230/KOSCAS.2020.58.089
  • 16Koo. D. H., & Lee. K. H. (2023). An Effect on Attitudes towards AI Technology by Using of Educational Programs Utilizing a Natural Language Processing Chatbot. JOURNAL OF The Korean Association of information Education, 27.4, 443-452.

※ 기관로그인 시 무료 이용이 가능합니다.

  • 4,200원

0개의 논문이 장바구니에 담겼습니다.