CAREER: Voice Technologies for Helping Older Adults Navigate Uncertain Information in Decision Making

该奖项全部或部分由《2021年美国救援计划法案》（公法117-2）资助。人们通常会制定策略来确定他们在网上遇到的信息是否可信。例如，他们可能会评估网站的结构、专业性或其他设计特征。然而，当使用语音技术搜索信息时，这些策略中的许多都没有帮助，其中许多缺乏屏幕，因此不能提供视觉可信度线索。此外，老年人经常使用语音技术来解决视力、运动和认知障碍带来的可访问性挑战，他们也往往更容易受到相互矛盾或不确定的信息的影响，这些信息是医疗保健等重要主题的特征。综上所述，这些因素使老年人在上网获取信息时更容易做出冒险的决定。本项目研究开发语音技术的方法，帮助老年人进行可信度评估，管理不确定或不一致的信息，并做出明智的决定。这项工作将提高老年人如何使用语音技术在线搜索信息的知识，开发非视觉信息搜索模型，并创造与语音助手和信息交互的新方法，以减少这些风险。该项目利用行为改变研究来调查如何在使用语音技术时推动老年人做出更好的信息决策。为此，研究小组将邀请老年人作为社区伙伴，不仅参与数据收集，而且作为研究小组的成员。本研究将(1)为老年人使用语音界面时的信息行为提供实证证据；(2)评估基于语音的信息搜索和决策的一系列选择架构策略，利用研究结果为非视觉信息搜索框架的设计提供信息；(3)通过一套新颖的音频工具来实现设计框架；(4)使用这些工具，评估它们在老年人“野外”减轻信息不确定性方面的有效性。这项工作的成果将推动人机交互、信息检索和语义以及衰老的研究。此外，由于语音界面设计在计算机教育中的研究不足，本项目也将为初高中学生的语音应用设计教学提供新的模块。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).People often create strategies for determining if the information they encounter online is credible. For example, they may evaluate the website’s structure, professionalism, or other design features. However, many of these strategies are not helpful when searching for information when using voice technologies, many of which lack screens and thus don’t present visual credibility cues. Further, older adults, who often use voice technologies to address accessibility challenges posed by vision, motor, and cognitive disabilities, are also often more susceptible to contradictory or uncertain information that characterizes important topics such as healthcare. Combined, these factors place older adults at greater risk of making risky decisions when accessing information online. This project investigates approaches for developing voice technologies that help older adults with credibility assessment, managing uncertain or inconsistent information, and making informed decisions. The work will advance knowledge about how older adults use voice technologies in seeking information online, develop models for non-visual information seeking, and create new ways of interacting with voice assistants and information to reduce these risks. This project draws upon behavior change research to investigate how to nudge older adults towards better information decisions when using voice technologies. To do so, the research team will engage older adults as community partners, not only in involved in data collection, but also as members of the research team. The research will (1) provide empirical evidence of older adults’ information behaviors when using voice interfaces; (2) evaluate a range of choice architecture strategies for voice-based information seeking and decision-making, using findings to inform the design of a framework for non-visual information seeking; (3) implement the design framework through a toolkit of novel audio tools; and (4) deploy these tools, evaluating their effectiveness at mitigating information uncertainty “in-the-wild” with older adults. The outcomes of the work will advance research in human computer interaction, information retrieval and sensemaking, and aging. Further, as voice interface design is understudied in computing education, this project will also contribute new modules for teaching voice application design to middle and high school students.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.