Informatization Policy (정보화정책)

National Information Society Agency (한국지능정보사회진흥원)
권호 표지
DOI QR코드

DOI QR Code

Understanding the User Experiences of Mental Health Chatbots by Intervention Type: A Topic Modeling Approach

토픽 모델링을 통한 심리상담 챗봇의 개입 유형별 사용자 경험 분석

  • 주희 (동국대학교 경영대학 경영정보학과) ;
  • 권소연 (동국대학교 경영대학 경영정보학과)
  • Received : 2025.05.22
  • Accepted : 2025.07.15
  • Published : 2025.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

The recent advancements in generative AI has led to the widespread adoption of mental health chatbots that enhance individuals' access to self-help psychological support. Despite the growing academic interest, however, efforts to examine user experiences across different intervention types remain limited. This study examined the user experiences between two types of interventions: companionship-based and CBT-based chatbots. We collected approximately 130,000 English-language reviews from two representative apps-Replika and Wysa-and applied Latent Dirichlet Allocation (LDA) to extract key user experience topics. These topics were then mapped onto five overarching themes for structured comparison. The findings revealed that interactivity-related themes were predominant in Replika reviews, whereas themes related to psychological support and CBT-specific interventions were more salient in Wysa. Through a large-scale analysis of user-generated text, this paper advances understanding of chatbot user experiences across intervention types and offers insights into tailored design strategies and data privacy policies.

최근 생성형 AI 기술의 발전으로 심리상담 챗봇은 개인의 심리 건강 관리 접근성을 획기적으로 높이며 빠르게 확산되고 있다. 이에 따라 학술적 관심도 높아지고 있으나, 개입 유형별 사용자 경험을 실증적으로 비교한 연구는 부족한 실정이다. 본 연구는 동반자형과 인지행동지료(CBT) 기반형이라는 개입 유형에 따라 사용자 경험의 차이를 실증적으로 분석하고자 하였다. 각 유형을 대표하는 Replika와 Wysa의 영문 리뷰 약 13만 건을 수집하여 LDA 토픽 모델링을 수행한 후, 도출된 토픽의 차이를 분석하고, 이를 다섯 가지 상위 차원으로 분류하여 유형별 사용자 경험을 체계적으로 비교하였다. 동반자형은 몰입감 있는 상호작용 경험이, CBT 기반형은 구체적인 심리건강 지원 및 CBT 개입 지원이 핵심 사용자 경험으로 나타났다. 본 연구는 대규모 리뷰 텍스트 기반의 정량 분석을 통해 심리상담 챗봇의 개입 유형별 사용자 경험 특성을 규명하고, 개입 방식에 따른 맞춤형 설계와 개인정보 보호를 고려한 정책적 시사점을 제시하였다.

Keywords

References

  1. 김법연 (2024). 생성형 AI의 법적 문제와 규제 논의 동향 <정보화정책>, 31권 3호, 3-33. https://doi.or.kr/10.22693/NIAIP.2024.31.3.003
  2. 김지근·양현정·이지원 (2021). 음성기반 심리상담 에이전트의 활용가능성 탐색 연구. <한국콘텐츠학회논문지>, 21권 7호, 144-156. https://doi.or.kr/10.5392/JKCA.2021.21.07.144
  3. 범설·권소연 (2024). 체중조절 앱에 대한 도움요청과 활용의지의 이해: 이성적 또는 감성적 타입에 따른 낙인효과의 상호작용을 중심으로, <정보화정책>, 31권 3호, 72-87. https://doior.kr/10.22693/NIAIP.2024.31.3.072
  4. BBC 뉴스코리아 (2024). AI 챗봇에 정신건강 상담 받는 MZ세대. https://www.bbc.com/korear/articles/c4nylqd7p7wo
  5. 양나은·고은희·최준호 (2025). 디지털 정신 건강 챗봇의 사용자 경험과 개선 방향: 텍스트 마이닝을 통한 인터랙션 비교 분석. <한국콘텐츠학회논문지>, 25권 1호, 161-175. https://doi.or.kr/10.5392/JKCA.2025.25.01.074
  6. 이아라·김효창·차민철·지용구 (2019). 상담 이론 기반의 심리상담 챗봇을 활용한 내담자 경험 연구. <대한인간공학회지>, 38권 3호, 161-175. http://doi.or.kr/10.5143/JESK.2019.38.3.161
  7. 장창기·허덕원·성육준 (2023). 인공지능 기반 음성비서 서비스의 지속이용 의도에 미치는 영향: 인공지능에 대한 신뢰와 프라이버시 염려의 상호작용을 중심으로. <정보화정책>, 30권 2호, 22-45. https://doi.or.kr/10.22693/NIAIP.2023.30.2.022
  8. 정해진·이진혁 (2022). 마이데이터 이용자의 프라이버시 태도와 보호의도에 관한 연구: 프라이버시 냉소주의의 영향. <정보화정책>, 29권 2호, 37-65. https://doi.or.kr/10.22693/NIAIP.2022.29.2.037
  9. Abd-Alrazaq, A. A., Alajlani, M., Ali, N., Denecke, K., Bewick, B. M. & Househ, M. (2021). Perceptions and opinions of patients about mental health chatbots: A scoping review. Journal of Medical Internet Research, 23(1), e17828. https://doi.org/10.2196/17828
  10. Ahmed, A., Aziz, S., Khalifa, M., Shah, U., Hassan, A., Abd-Alrazaq, A. & Househ, M. (2022). Thematic analysis on user reviews for depression and anxiety chatbot apps: Machine learning approach. JMIR Formative Research, 6(3), e27654. https://doi.org/10.2196/27654
  11. American Psychiatric Association (2025). Digital mental health. https://www.psychiatry.org:443/psychiatrists/practice/digital-mental-health
  12. Blei, D. M., Ng, A. Y. & Jordan, M. I. (2003). Latent dirichlet allocation. Journal of Machine Learning Research, 3, 993-1022. https://doi.org/10.1162/jmlr.2003.3.4-5.993
  13. Chaudhry, B. M. & Debi, H. R. (2024). User perceptions and experiences of an AI-driven conversational agent for mental health support. Mhealth, 10, 22-22. https://doi.org/10.21037/mhealth-23-55
  14. Cheng, M. & Jin, X. (2019). What do Airbnb users care about? An analysis of online review comments. International Journal of Hospitality Management, 76, 58-70. https://doi.org/10.1016/j.ijhm.2018.04.004
  15. Darko, A. P., Antwi, C. O., Adjei, K., Zhang, B. & Ren, J. (2024). Predicting determinants influencing user satisfaction with mental health app: An explainable machine learning approach based on unstructured data. Expert Systems with Applications, 249, 123647. https://doi.org/10.1016/j.eswa.2024.123647
  16. Denecke, K., Schmid, N. & Nüssli, S. (2022). Implementation of cognitive behavioral therapy in e-mental health apps: Literature review. Journal of Medical Internet Research, 24(3), e27791. https://doi.org/10.2196/27791
  17. Haque, M. D. R. & Rubya, S. (2023). An overview of chatbot-based mobile mental health apps: Insights from app description and user reviews. JMIR Mhealth and Uhealth, 11, e44838. https://doi.org/10.2196/44838
  18. He, Y., Yang, L., Zhu, X., Wu, B., Zhang, S., Qian, C. & Tian, T. (2022). Mental health chatbot for young adults with depressive symptoms during the Covid-19 Pandemic: Single-blind, three-arm randomized controlled trial. Journal of Medical Internet Research, 24(11), e40719. https://doi.org/10.2196/preprints.40719
  19. Hu, N., Zhang, T., Gao, B. & Bose, I. (2019). What do hotel customers complain about? Text analysis using structural topic model. Tourism Management, 72, 417-426. https://doi.org/10.1016/j.tourman.2019.01.002
  20. Inal, Y., Wake, J. D., Guribye, F. & Nordgreen, T. (2020). Usability evaluations of mobile mental health technologies: Systematic review. Journal of Medical Internet Research, 22(1), e15337. https://doi.org/10.2196/15337
  21. Inkster, B., Sarda, S. & Subramanian, V. (2018). An empathy-driven, conversational artificial intelligence agent (WYSA) for digital mental well-being: Real-world data evaluation mixed-methods study. JMIR Mhealth and Uhealth, 6(11), e12106. https://doi.org/10.2196/12106
  22. Kabat-Zinn, J. (2003). Mindfulness-based interventions in context: Past, present, and future. Clinical Psychology: Science and Practice, 10(2), 144-156. https://doi.org/10.1093/clipsy/bpg016
  23. Kim, M., Lee, S., Kim, S., Heo, J., Lee, S., Shin, Y. B., Cho, C. H. & Jung, D. (2025). Therapeutic potential of social chatbots in alleviating loneliness and social anxiety: Quasi-experimental mixed methods study. Journal of Medical Internet Research, 27, e65589. https://doi.org/10.2196/65589
  24. Koek, W. J. D. & Chen, V. H. H. (2025). My avatar makes me feel good? The effect of avatar personalisation and virtual agent interactions on self-esteem. Behaviour & Information Technology, 44(4), 843-858. https://doi.org/10.1080/0144929x.2024.2349176
  25. Lee, S., Lee, N. & Sah, Y. J. (2020). Perceiving a mind in a chatbot: Effect of mind perception and social cues on co-presence, closeness, and intention to use. International Journal of Human-Computer Interaction, 36(10), 930-940. https://doi.org/10.1080/10447318.2019.1699748
  26. Limpanopparat, S., Gibson, E. & Harris, D. A. (2024). User engagement, attitudes, and the effectiveness of chatbots as a mental health intervention: A systematic review. Computers in Human Behavior: Artificial Humans, 2(2), 100081. https://doi.org/10.1016/j.chbah.2024.100081
  27. Lovett, L. (2025, April 23). Woe is me: Woebot says farewell to signature app. Behavioral Health Business. https://bhbusiness.com/2025/04/23/woe-is-me-woebot-says-farewell-to-signature-app/
  28. Mani, M., Kavanagh, D. J., Hides, L. & Stoyanov, S. R. (2015). Review and evaluation of mindfulness-based iphone apps. JMIR Mhealth and Uhealth, 3(3), e82. https://doi.org/10.2196/mhealth.4328
  29. Martin, F. & Johnson, M. (2015, December 8-9). More efficient topic modelling through a noun-only approach. Australasian Language Technology Association Workshop, Parramatta, NSW, Australia.
  30. Meng, J., Rheu, M., Zhang, Y., Dai, Y. & Peng, W. (2023, April 23-28). Mediated social support for distress reduction: AI chatbots vs human. ACM on Human-Computer Interaction, Hamburg, Germany. https://doi.org/10.1145/3579505
  31. Nißen, M., Rüegger, D., Stieger, M., Flückiger, C., Allemand, M., v Wangenheim, F. & Kowatsch, T. (2022). The effects of healthcare chatbot personas with different social roles on the client-chatbot bond and usage intentions: Development of a design codebook and web-based study. Journal of Medical Internet Research, 24(4), e32630. https://doi.org/10.2196/32630
  32. Replika (2025). The AI companion who cares. https://replika.com
  33. Research and Markets (2021). Global emerging mental health devices and platforms market: Analysis and forecast, 2021-2030. https://www.researchandmarkets.com/reports/5315021/global-emerging-mental-health-devices-and
  34. Shan, Y., Ji, M., Xie, W., Lam, K. Y. & Chow, C. Y. (2022). Public trust in artificial intelligence applications in mental health care: Topic modeling analysis. JMIR Human Factors, 9(4), e38799. https://doi.org/10.2196/38799
  35. Strohmann, T., Siemon, D., Khosrawi-Rad, B. & Robra-Bissantz, S. (2023). Toward a design theory for virtual companionship. Human-Computer Interaction, 38(3-4), 194-234. https://doi.org/10.1080/07370024.2022.2084620
  36. Ta, V., Griffith, C., Boatfield, C., Wang, X., Civitello, M., Bader, H., DeCero, E. & Loggarakis, A. (2020). User experiences of social support from companion chatbots in everyday contexts: Thematic analysis. Journal of Medical Internet Research, 22(3), e16235. https://doi.org/10.2196/16235
  37. Wenzel, A. (2017). Basic strategies of cognitive behavioral therapy. Psychiatric Clinics of North America, 40(4), 597-609. https://doi.org/10.1016/j.psc.2017.07.001
  38. World Health Organization (2016). Investing in treatment for depression and anxiety leads to fourfold return. https://www.who.int/news/item/13-04-2016-investing-in-treatment-for-depression-and-anxiety-leads-to-fourfold-return
  39. World Health Organization (2022). World mental health report: Transforming mental health for all. https://www.who.int/publications/i/item/9789240049338
  40. WYSA (2025). Your personal wellbeing coach. https://www.wysa.com/for-individuals
  41. Xue, J., Zhang, B., Zhao, Y., Zhang, Q., Zheng, C., Jiang, J. & Li, H. (2023). Evaluation of the current state of chatbots for digital health: A scoping review. Journal of Medical Internet Research, 25, e47217. https://doi.org/10.2196/47217