{"title":"基于对话的混合用户界面(UI),适用于复述网格技术:定性调查自动化实验室实验","authors":"Yunxing Liu, Jean-Bernard Martens","doi":"10.1016/j.ijhcs.2024.103227","DOIUrl":null,"url":null,"abstract":"<div><p>A frequent use of conversational user interfaces (CUIs) today is improving the users’ experience with online quantitative surveys. In this paper, we explore the use of CUIs in qualitative surveys. As a concrete use case, we adopt a specific, well-structured, qualitative research method called the repertory grid technique (RGT). We developed a hybrid user interface (HUI) that combines a graphical user interface (GUI) with a CUI to automate the distinct stages in a RGT survey. A pilot study was used to verify the feasibility of the approach and to fine-tune interface aspects of an initial prototype. In this paper, we report the results of a within-subject lab experiment with 24 participants that aimed to establish the performance and UX in a realistic context of a more advanced prototype. We observed a small decrease in UX in some hedonistic aspects, but also confirmed that the HUI performs similarly to a human agent in most pragmatic aspects. These results provide support for our hypothesis that automating qualitative surveys is possible with proper interface design. We hope that our work can inspire other researchers to design additional tools for qualitative survey automation, especially now that generative AI systems, such as ChatGPT, open up interesting new ways for computer systems to interact with users in natural language.</p></div>","PeriodicalId":54955,"journal":{"name":"International Journal of Human-Computer Studies","volume":null,"pages":null},"PeriodicalIF":5.3000,"publicationDate":"2024-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1071581924000119/pdfft?md5=b5156751be2815710e3593dfca7dd4ef&pid=1-s2.0-S1071581924000119-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Conversation-based hybrid UI for the repertory grid technique: A lab experiment into automation of qualitative surveys\",\"authors\":\"Yunxing Liu, Jean-Bernard Martens\",\"doi\":\"10.1016/j.ijhcs.2024.103227\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>A frequent use of conversational user interfaces (CUIs) today is improving the users’ experience with online quantitative surveys. In this paper, we explore the use of CUIs in qualitative surveys. As a concrete use case, we adopt a specific, well-structured, qualitative research method called the repertory grid technique (RGT). We developed a hybrid user interface (HUI) that combines a graphical user interface (GUI) with a CUI to automate the distinct stages in a RGT survey. A pilot study was used to verify the feasibility of the approach and to fine-tune interface aspects of an initial prototype. In this paper, we report the results of a within-subject lab experiment with 24 participants that aimed to establish the performance and UX in a realistic context of a more advanced prototype. We observed a small decrease in UX in some hedonistic aspects, but also confirmed that the HUI performs similarly to a human agent in most pragmatic aspects. These results provide support for our hypothesis that automating qualitative surveys is possible with proper interface design. We hope that our work can inspire other researchers to design additional tools for qualitative survey automation, especially now that generative AI systems, such as ChatGPT, open up interesting new ways for computer systems to interact with users in natural language.</p></div>\",\"PeriodicalId\":54955,\"journal\":{\"name\":\"International Journal of Human-Computer Studies\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-01-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S1071581924000119/pdfft?md5=b5156751be2815710e3593dfca7dd4ef&pid=1-s2.0-S1071581924000119-main.pdf\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Human-Computer Studies\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1071581924000119\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, CYBERNETICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Human-Computer Studies","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1071581924000119","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, CYBERNETICS","Score":null,"Total":0}
引用次数: 0
摘要
如今,对话式用户界面 (CUI) 的一个常用功能是改善用户在线定量调查的体验。在本文中,我们将探讨 CUI 在定性调查中的应用。作为一个具体的使用案例,我们采用了一种特定的、结构良好的定性研究方法,即复述网格技术(RGT)。我们开发了一种混合用户界面 (HUI),它将图形用户界面 (GUI) 与 CUI 结合在一起,实现了 RGT 调查不同阶段的自动化。我们利用试点研究验证了该方法的可行性,并对初始原型的界面方面进行了微调。在本文中,我们报告了一项有 24 名参与者参加的主体内实验室实验的结果,该实验旨在确定更先进原型在现实环境中的性能和用户体验。我们观察到用户体验在某些享乐主义方面略有下降,但也证实 HUI 在大多数实用性方面的表现与人类代理类似。这些结果为我们的假设提供了支持,即通过适当的界面设计,定性调查是可以实现自动化的。我们希望我们的工作能激励其他研究人员为定性调查自动化设计更多的工具,尤其是现在像 ChatGPT 这样的生成式人工智能系统为计算机系统用自然语言与用户交互开辟了有趣的新途径。
Conversation-based hybrid UI for the repertory grid technique: A lab experiment into automation of qualitative surveys
A frequent use of conversational user interfaces (CUIs) today is improving the users’ experience with online quantitative surveys. In this paper, we explore the use of CUIs in qualitative surveys. As a concrete use case, we adopt a specific, well-structured, qualitative research method called the repertory grid technique (RGT). We developed a hybrid user interface (HUI) that combines a graphical user interface (GUI) with a CUI to automate the distinct stages in a RGT survey. A pilot study was used to verify the feasibility of the approach and to fine-tune interface aspects of an initial prototype. In this paper, we report the results of a within-subject lab experiment with 24 participants that aimed to establish the performance and UX in a realistic context of a more advanced prototype. We observed a small decrease in UX in some hedonistic aspects, but also confirmed that the HUI performs similarly to a human agent in most pragmatic aspects. These results provide support for our hypothesis that automating qualitative surveys is possible with proper interface design. We hope that our work can inspire other researchers to design additional tools for qualitative survey automation, especially now that generative AI systems, such as ChatGPT, open up interesting new ways for computer systems to interact with users in natural language.
期刊介绍:
The International Journal of Human-Computer Studies publishes original research over the whole spectrum of work relevant to the theory and practice of innovative interactive systems. The journal is inherently interdisciplinary, covering research in computing, artificial intelligence, psychology, linguistics, communication, design, engineering, and social organization, which is relevant to the design, analysis, evaluation and application of innovative interactive systems. Papers at the boundaries of these disciplines are especially welcome, as it is our view that interdisciplinary approaches are needed for producing theoretical insights in this complex area and for effective deployment of innovative technologies in concrete user communities.
Research areas relevant to the journal include, but are not limited to:
• Innovative interaction techniques
• Multimodal interaction
• Speech interaction
• Graphic interaction
• Natural language interaction
• Interaction in mobile and embedded systems
• Interface design and evaluation methodologies
• Design and evaluation of innovative interactive systems
• User interface prototyping and management systems
• Ubiquitous computing
• Wearable computers
• Pervasive computing
• Affective computing
• Empirical studies of user behaviour
• Empirical studies of programming and software engineering
• Computer supported cooperative work
• Computer mediated communication
• Virtual reality
• Mixed and augmented Reality
• Intelligent user interfaces
• Presence
...