ChatGPT 기반 피부 상담챗봇에서 프롬프트 엔지니어링 기법을 활용한 사용자 실험
User Experiment with Prompt Engineering Techniques in a ChatGPT-Based Dermatology Consultation Chatbot
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 연구는 ChatGPT를 활용한 헬스케어 분야 챗봇의 사용자 만족도 향상 방법을 실험적으로 탐구하는 것을 목표로 한다. 이를 위해 본 연구는 ChatGPT를 활용한 피부 상담 챗봇 서비스인 ‘Dewy’를 개발하였고, 프롬프트 엔지니어링 기법에 대해 실험적인 접근 방법으로 사용자 만족도 향상 방안을 탐구하였다. 피부 질환은 개인의 건강과 자존감에 큰 영향을 미치지만, 피부과 방문의 비용과 접근성 문제로 적시 치료를 받지 못하는 경우가 많다. ‘Dewy’는 이러한 문제를 해결하기 위해 피부과 전문가의 페르소나를 사용하여, ‘인지 검증’ 기법을 적용한 5가지 유형의 대화용 프롬프트를 설계하였다. 총 57명의 사용자가 참여한 설문조사 결과, 초기 질문에 답변을 제공하면서 후속 질문에 선택적 답변을 요구한 챗봇이 사용자 만족도가 가장 높았으며, 특히 효율성과 학습 용이성에서 좋은 평가를 받았다. 본 연구 결과는 ChatGPT와 같은 대용량 언어 모델 기반의 챗봇이 전통적인 피부과 상담 방식에 대한 혁신적인 대안이 될 수 있는 가능성을 보여주고 있다.
Abstract
This research experimentally investigates the enhancement of user satisfaction within the healthcare domain by utilizing ChatGPT. We introduced ‘Dewy’, a skin consultation chatbot service designed with ChatGPT, and delved into enhancing user contentment by pioneering prompt engineering techniques. Given the profound implications of skin diseases on one’s health and self-worth, and the prevailing barriers of cost and accessibility to dermatological care, there’s a pertinent need for innovative solutions. In response, Dewy was equipped with a dermatologist persona and instantiated five distinct conversational prompts derived from cognitive validation methods. Based on feedback from 57 participants, the chatbot strategy of addressing preliminary inquiries and providing optional follow-up queries demonstrated the highest user satisfaction. It was notably commended for its operational efficiency and user-friendliness. Our findings underscore the prospective role of large language model-based chatbots, like ChatGPT, in revolutionizing the landscape of dermatological consultations.
참고문헌 (23)
- 박요한, "차량 내 음성비서의 수용 의도에 영향을 미치는요인 연구: 확장된 통합기술수용모델을 중심으로", 한국혁신학회지, 16(3), pp.1~43 (2021), 한국혁신학회
- 최선아, "특허데이터를 활용한 기술혁신 산업의 기술경쟁력 분석: 인공지능(AI) 스피커를 중심으로", 한국혁신학회지, 18(2), pp.55~75 (2023), 한국혁신학회
- "GPT4All: Training an Assistant-style Chatbot with Large Scale Data Distillation from GPT-3.5-Turbo" (2023)[URL]
- Bangor, A., "Determining What Individual SUS Scores Mean : Adding an Adjective Rating Scale", Journal of Usability Studies, 4(3), pp.114~123 (2009)
- Bates, M., "Health Care Chatbots Are Here to Help", IEEE Pulse, 10(3), pp.12~14 (2019)
- Bickers, D. R., "The burden of skin diseases : 2004 : A joint project of the American Academy of Dermatology Association and the Society for Investigative Dermatology", Journal of the American Academy of Dermatology, 55(3), pp.490~500 (2006)
- Brooke, J., "SUS : A Retrospective", Journal of Usability Studies, 8(2), pp.29~40 (2013)
- Brown, T., "Language models are few-shot learners", Advances in neural information processing systems, 33, pp.1877~1901 (2020)
- Calton, B., "Telemedicine in the Time of Coronavirus", Journal of Pain and Symptom Management, 60(1), pp.e12~e14 (2020)[DOI]
- Chowdhery, A, "Palm : Scaling language modeling with pathways", arXiv preprint arXiv:2204.02311, ~ (2022)
- Christiano, P.F, "Deep Reinforcement Learning from Human Preferences", Advances in Neural Information Processing Systems (2017)
- Chowdhery, A, "Palm: Scaling language modeling with pathways", arXiv preprint arXiv:2204.02311, ~ (2022)
- Dede, C., "Learning Engineering for Online Education: Theoretical Contexts and Design-Based Examples" (2018), Routledge
- Gupta, J., "Florence- A Health Care Chatbot", 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), pp.504~508 (2006)
- Holmes, S, "Usability Testing of a Healthcare Chatbot: Can we use Conventional Methods to Assess Conversational User Interfaces?", Proceedings of the 31st European Conference on Cognitive Ergonomics (ECCE 2019), pp.207~214 (2019)
- Hsu, I-C., "A medical Chatbot using machine learning and natural language under-standing", Multimedia Tools and Applications, 81(17), pp.23777~23799 (2022)
- Kamita, T., "A Chatbot System for Mental Healthcare Based on SAT Counseling Method", Mobile Information Systems, 2019 (2019)[DOI]
- Lewis, J., "The Factor Structure of the System Usability Scale", Proceedings of the 1st International Conference on Human Centered Design: Held as Part of HCI International, pp.94~103 (2009)
- Lewis, J. R., "The System Usability Scale : Past, Present, and Future", International Journal of Human-Computer Interaction, 34(7), pp.577~590 (2018)
- (2023)[URL]
- Ouyang, L., "Training language models to follow instructions with human feedback", Advances in Neural Information Processing Systems, 35, pp.27730~27744 (2022)
- Raffel, C., "Exploring the limits of transfer learning with a unified text-to-text transformer", The Journal of Machine Learning Research, 21(1), pp.5485~5551 (2020)
- The Paradox of Artificial Intelligence (AI) and Privacy: Focusing on AI Voice Assistants, "Shim, Hong-Jin", KISDI, ~ (2018)