田野研究是不可替代的,但成本高、耗时且容易出错,需要精心准备。受制造业快速原型设计的启发,我们提出了一种快速、低成本的评估方法,利用视觉语言模型(VLM)人设来模拟与田野研究结果相当的成果。尽管LLM展示了类人推理和语言能力,但自动驾驶(AV)与行人交互需要空间意识、情感共情和行为生成。这引发了我们的研究问题:VLM人设能有多大程度地模仿田野研究中的人类响应?我们进行了平行研究:1)一项有20名参与者的真实世界研究;2)一项使用20个VLM人设的视频研究,两者均针对过街任务。我们比较了它们的响应,并采访了五位人机交互(HCI)研究人员探讨潜在应用。结果显示,VLM人设能够模仿人类响应模式(例如平均过街时间为5.25秒 vs. 5.07秒),但缺乏行为的多样性和深度。它们在形成性研究、田野研究准备和人类数据增强方面显示出潜力。
英文摘要:
Field studies are irreplaceable but costly, time-consuming, and error-prone, which need careful preparation. Inspired by rapid-prototyping in manufacturing, we propose a fast, low-cost evaluation method using Vision-Language Model (VLM) personas to simulate outcomes comparable to field results. While LLMs show human-like reasoning and language capabilities, autonomous vehicle (AV)-pedestrian interaction requires spatial awareness, emotional empathy, and behavioral generation. This raises our research question: To what extent can VLM personas mimic human responses in field studies? We conducted parallel studies: 1) one real-world study with 20 participants, and 2) one video-study using 20 VLM personas, both on a street-crossing task. We compared their responses and interviewed five HCI researchers on potential applications. Results show that VLM personas mimic human response patterns (e.g., average crossing times of 5.25 s vs. 5.07 s) lack the behavioral variability and depth. They show promise for formative studies, field study preparation, and human data augmentation.
Characterizing LLM-Based Family Education through the Lens of Activity Theory: A Scoping Review of the HCI Literature
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Nan Kai university(南开大学);The Hong Kong University of Science and Technology(香港科技大学);Tsinghua University(清华大学)
Improving Human-Computer Interaction by Developing Culture-sensitive Applications based on Common Sense Knowledge
Web 3.0的出现,要求交互系统的个性化(Lassila & Hendler,2007),以及在充斥着计算机系统和设备的未来社会中对能够以更自然的方式交互的系统的需求(Harper等人,2008年)表明,应该在HCI方面取得重大进展。本章介绍了一些贡献的LIA的未来的人机交互,捍卫使用常识知识是一种可能性,以改善人机交互,特别是因为人们分配的意义,他们的消息的基础上,他们的常识,因此,使用这些知识在开发用户界面可以使他们更直观的最终用户。此外,由于常识知识因群体而异,因此可以用于开发能够为不同目标群体提供不同反馈的应用程序,正如本章介绍的应用程序所示,通过这种方式,可以考虑到文化问题的界面个性化。为了在计算机系统的开发和设计中使用常识性知识,有必要提供一个允许它的体系结构。本章介绍了LIA用于常识性知识获取、表示和使用以及自然语言处理的方法,有助于那些打算进入这个充满挑战的世界的人开始。
Avatar Visual Similarity for Social HCI: Increasing Self-Awareness
German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));LIACS, Universiteit Leiden(莱顿大学LIACS学院);Vrije Universiteit Amsterdam(阿姆斯特丹自由大学);Saarland University(萨尔大学)
Can GPT-4o Evaluate Usability Like Human Experts? A Comparative Study on Issue Identification in Heuristic Evaluation
State University of Paraná(巴拉那州立大学);Federal Technological University of Paraná(巴拉那联邦技术大学);Federal University of Lavras(拉夫拉斯联邦大学);Federal Rural University of Pernambuco(伯南布哥联邦农村大学);Federal University of São Carlos(圣卡洛斯联邦大学)
Dynamic User Interface Generation for Enhanced Human-Computer Interaction Using Variational Autoencoders
University of Southern California(南加州大学);School of Visual Arts(视觉艺术学院);Georgia Institute of Technology(佐治亚理工学院);Carnegie Mellon University(卡内基梅隆大学);New York University(纽约大学)
"I Like Sunnie More Than I Expected!": Exploring User Expectation and Perception of an Anthropomorphic LLM-based Conversational Agent for Well-Being Support
University of Toronto(多伦多大学);Flourish Science(弗洛里什科学公司);Northeastern University(东北大学)
Human-Computer Interaction Institute, Carnegie Mellon University(卡内基梅隆大学人机交互研究所);University of Washington(华盛顿大学);Institute of Educational Research, Ruhr-Universität Bochum(鲁尔大学波鸿分校教育研究所)