DOI QR코드

DOI QR Code

대화형 에이전트의 자기발화수정 전략이 사용자 경험에 미치는 영향 - 과업 중요도와 대화 오류 여부를 중심으로

Effects of Conversational Agent's Self-Repair Strategy On User Experience - Focused on Task Criticality and Conversational Error

  • 김환주 (연세대학교 정보대학원 UX트랙) ;
  • 김정용 (연세대학교 정보대학원 UX트랙) ;
  • 강현민 (연세대학교 정보대학원 UX트랙)
  • Kim, Hwanju (Department of UX, Graduate School of Information, Yonsei University) ;
  • Kim, Jung-Yong (Department of UX, Graduate School of Information, Yonsei University) ;
  • Kang, Hyunmin (Graduate School of Information, Yonsei University)
  • 투고 : 2021.12.16
  • 심사 : 2022.02.20
  • 발행 : 2022.02.28

초록

기술의 발달과 스마트 스피커 보급의 증가에도, 스마트 스피커의 대화 오류로 사용자 만족도는 하락하고 있다. 이 연구는 스마트 스피커의 대화형 에이전트 맥락에서 '자기발화수정 전략'이 과업 중요도 수준과 대화 오류 여부에 따라 사용자 경험에 미치는 영향을 살펴보았다. 대화 오류에 따라 시나리오를 제작하고 과업 중요도 수준에 따라 집단을 나눠 실험을 진행해 신뢰, 지각된 유용성, 지각된 용이성, 수용의도를 측정하였다. 연구 결과, 에이전트의 자기발화수정 전략은 완전한 수행과 비교해 신뢰와 지각된 용이성에 부적 영향을 주며, 과업 중요도와의 상호작용을 통해 수용의도에 영향을 미치는 것을 발견하였다. 이 연구는 대화형 에이전트 연구에서 미흡했던 자기발화수정 전략의 효과를 실증적으로 알아보았고, 자기발화수정 전략의 수용과 관련된 사용자 경험 요인을 살펴보았다는 점에서 의의를 가진다.

Despite the development of technology and the increase in the spread of smart speakers, user satisfaction keeps decreasing due to conversational errors. This study aims to examine the effect of the self-repair strategy on user experience in the context of conversational agents of smart speakers. Scenarios were designed based on error situations, and participants were divided into two groups by task criticality. The results revealed that the agent's self-repair strategy has a negative effect on trust and perceived ease of use compared with performance without error. It also influenced adoption intention through interaction with task criticality. This study is significant in that it empirically investigated the effects of the self-repair strategy and the user experience factors related to the actual acceptance of the self-repair strategy.

키워드

참고문헌

  1. Consumer Insight. (23 Mar, 2021). Consumer Insight. Telecommunication report . https://www.consumerinsight.co.kr/voc_view.aspx?no=3170&id=ins02_list&PageNo=1&schFlag=0
  2. K. S. Suh. (2020). A Study on Self-Repair Speech by Native Korean Speakers. Doctoral dissertation. Seoul National University, Seoul.
  3. A. Chanseau, K. Dautenhahn, K. L. Koay, M. L. Walters, G. Lakatos, & M. Salem. (2019). How does peoples' perception of control depend on the criticality of a task performed by a robot. Paladyn, Journal of Behavioral Robotics, 10(1), 380-400. DOI : 10.1515/pjbr-2019-0030
  4. H. A. Yanco & J. L. Drury. (2004). Classifying human-robot interaction: an updated taxonomy. In 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No. 04CH37583). (pp. 2841-2846). Hague : IEEE. DOI : 10.1109/ICSMC.2004.1400763
  5. N. Ezer, A. D. Fisk, & W. A. Rogers. (2009). More than a servant: Self-reported willingness of younger and older adults to having a robot perform interactive and critical tasks in the home. In Proceedings of the human factors and ergonomics society annual meeting. (pp. 136-140). Los Angeles : SAGE Publications. DOI : 10.1177/154193120905300206.
  6. S. G. Tzafestas. (2016). Sociorobot World. Cham : Springer.
  7. Y. M. Lee, S. J. Park, & H. J. Suk. (2018). Applying Social Strategies for Breakdown Situations of Conversational Agents: A Case Study using Forewarning and Apology. Science of emotion & sensibility, 21(1), 59-70. DOI : 10.14695/KJSOS.2018.21.1.59
  8. S. M. Hong & K. S. Cho. (2018). Error recovery strategies to re-utterance in conversational agent's understanding error. Proceeding of HCI KOREA 2018. (pp. 730-734). Seoul : The HCI society of Korea.
  9. S. C. Levinson. (1983). Pragmatics. Cambridge : Cambridge University Press.
  10. E. A. Schegloff, G. Jefferson, & H. Sacks. (1977). The preference for self-correction in the organization of repair in conversation. Language, 53(2), 361-382. DOI : 10.2307/413107
  11. S. L. Purcell & B. Z. Liles. (1992). Cohesion repairs in the narratives of normal-language and language-disordered school-age children. Journal of Speech, Language, and Hearing Research, 35(2), 354-362. DOI : 10.1044/jshr.3502.354
  12. A. Cuadra, S. Li, H. Lee, J. Cho, & W. Ju. (2021). My Bad! Repairing Intelligent Voice Assistant Errors Improves Interaction. Proceedings of the ACM on Human-Computer Interaction, 5(CSCW1). 1-24. DOI : 10.1145/3449101
  13. K. Bousmalis, M. Mehu, & M. Pantic. (2013). Towards the automatic detection of spontaneous agreement and disagreement based on nonverbal behaviour: A survey of related cues, databases, and tools. Image and vision computing, 31(2), 203-221. DOI : 10.1016/j.imavis.2012.07.003
  14. L. Tavabi, K. Stefanov, S. Nasihati Gilani, D. Traum, & M. Soleymani. (2019). Multimodal learning for identifying opportunities for empathetic responses. In 2019 International Conference on Multimodal Interaction, (pp. 95-104). New York : Association for Computing Machinery. DOI : 10.1145/3340555.3353750
  15. D. Gefen, E. Karahanna, & D. W. Straub. (2003). Trust and TAM in Online Shopping: An Integrated Model. MIS Quarterly, 27(1), 51-90. DOI : 10.2307/30036519
  16. C. Van Slyke, F. Belanger, & C. L. Comunale. (2004). Factors influencing the adoption of web-based shopping: the impact of trust. ACM SIGMIS Database: the DATABASE for Advances in Information Systems, 35(2), 32-49. DOI : 10.1145/1007965.1007969
  17. C. H. Kang, H. Kim, & H. M. Kang. (2020). A study on the user experience according to the method and detail of recommendation agent's explanation facilities. The Journal of the Korea Contents Association, 20(8), 653-665. DOI : 10.5392/JKCA.2020.20.08.653
  18. E. T. Oh & G. H. Kwon. (2020). Effects of Perceived Anthropomorphism on Acceptance of Voice AI Agent - Focusing on the Comparison by Gender and Age - Journal of the HCI Society of Korea, 15(3), 31-42. DOI : 10.17210/jhsk.2020.09.15.3.31
  19. K. S. Lee, J. P. Yu, & S. A. Lim. (2020). A Study on Factors Affecting the Intention to Use Artificial Intelligence(AI) Speakers: Focusing on the Extended Technology Acceptance Model(E-TAM). The Society of Convergence Knowledge Transactions, 8(4), 59-69. DOI : 10.22716/sckt.2020.8.4.036
  20. J. M. Lee, M. J. Jung, J. R. Lee, Y. E. Kim, & C. Y. An. (2019). Consumer Perception and Adoption Intention of Artificial Intelligent Speaker: Non-Users Perspective. Journal of Consumer Studies, 30(2), 193-213. DOI : 10.35736/JCS.30.2.9
  21. K. Seaborn, N. P. Miyake, P. Pennefather, & M. Otake-Matsuura. (2021). Voice in Human-Agent Interaction: A Survey. ACM Computing Surveys, 54(4), 1-43. DOI : 10.1145/3386867