UX Research on Conversational Human-AI Interaction: A Literature Review of the ACM Digital Library

UX Research on Conversational Human-AI Interaction: A Literature Review of the ACM Digital Library
复制标题

人机对话交互的用户体验研究:ACM 数字图书馆文献综述

DOI:
10.1145/3491102.3501855
复制
发表时间:
2022
期刊:
roceedings of the 2022 CHI Conference on Human Factors in Computing Systems
影响因子:
--
通讯作者:
Huang, Yun
Huang, Yun
中科院分区:
--
文献类型:
--
作者:
Zheng, Qingxiao;Tang, Yiliu;Liu, Yiren;Liu, Weizi;Huang, Yun

文献摘要

参考文献

被引文献

相似文献

早期的对话代理(CA)专注于人与CA之间的二元人-AI交互,随后,多元人-AI交互的日益流行,其中CA被设计为调解人与人的交互。多元互动的CA是独一无二的,因为它们包含混合的社会互动,即人与CA、人与人以及人与组的行为。然而,对多元CA的研究分散在不同的领域,这使得识别、比较和积累现有知识具有挑战性。为了促进未来CA系统的设计,我们对ACM出版物进行了文献综述,并确定了一组进行UX(用户体验)研究的作品。我们将多元认知结构的影响定性地综合为人与人之间交互的四个方面,即沟通、参与、联系和关系维持。通过对选定的多元和二元CA研究进行混合方法分析,我们开发了一套关于效果的评估措施。我们的发现表明,具有社会边界的设计,如隐私、披露和身份识别,对于伦理多元CA至关重要。未来的研究还应该推进对话式人工智能的可用性测试方法和信任建立指南。
Early conversational agents (CAs) focused on dyadic human-AI interaction between humans and the CAs, followed by the increasing popularity of polyadic human-AI interaction, in which CAs are designed to mediate human-human interactions. CAs for polyadic interactions are unique because they encompass hybrid social interactions, i.e., human-CA, human-to-human, and human-to-group behaviors. However, research on polyadic CAs is scattered across different fields, making it challenging to identify, compare, and accumulate existing knowledge. To promote the future design of CA systems, we conducted a literature review of ACM publications and identified a set of works that conducted UX (user experience) research. We qualitatively synthesized the effects of polyadic CAs into four aspects of human-human interactions, i.e., communication, engagement, connection, and relationship maintenance. Through a mixed-method analysis of the selected polyadic and dyadic CA studies, we developed a suite of evaluation measurements on the effects. Our findings show that designing with social boundaries, such as privacy, disclosure, and identification, is crucial for ethical polyadic CAs. Future research should also advance usability testing methods and trust-building guidelines for conversational AI.
探索结合人类专家通过聊天机器人提供日记指导的效果
DOI: 10.1145/3449196
发表时间: 2021
影响因子: --
作者:
Yi;Naomi Yamashita;Yun Huang
通讯作者: Yun Huang
概念隐喻影响人类与人工智能协作的看法
DOI: 10.1145/3415234
发表时间: 2020
影响因子: --
作者:
Khadpe, Pranav;Krishna, Ranjay;Fei-Fei, Li;Hancock, Jeffrey T.;Bernstein, Michael S.
通讯作者: Bernstein, Michael S.
DOI: --
发表时间: 2017
期刊: International Conference on Multimodal Interaction
影响因子: --
作者:
M. Ochs;Nathan Libermann;Axel Boidin;T. Chaminade
通讯作者: T. Chaminade
QuizBot:基于对话的事实知识自适应学习系统
DOI: --
发表时间: 2019
期刊: International Conference on Human Factors in Computing Systems
影响因子: --
作者:
S. Ruan;Liwei Jiang;Justin Xu;Bryce Joe;Zhengneng Qiu;Yeshuang Zhu;Elizabeth L. Murnane;E. Brunskill;J. Landay
通讯作者: J. Landay
作为结构和过程的话语
DOI: --
发表时间: 1997
期刊:
影响因子: --
作者:
T. V. Dijk
通讯作者: T. V. Dijk