Xinning Gui

Yuan Sun, Qiurong Song, Xinning Gui et al.

Automated machine learning (AutoML) is envisioned to make ML techniques accessible to ordinary users. Recent work has investigated the role of humans in enhancing AutoML functionality throughout a standard ML workflow. However, it is also critical to understand how users adopt existing AutoML solutions in complex, real-world settings from a holistic perspective. To fill this gap, this study conducted semi-structured interviews of AutoML users (N=19) focusing on understanding (1) the limitations of AutoML encountered by users in their real-world practices, (2) the strategies users adopt to cope with such limitations, and (3) how the limitations and workarounds impact their use of AutoML. Our findings reveal that users actively exercise user agency to overcome three major challenges arising from customizability, transparency, and privacy. Furthermore, users make cautious decisions about whether and how to apply AutoML on a case-by-case basis. Finally, we derive design implications for developing future AutoML solutions.

Xianghua Ding, Shuhan Wei, Xinning Gui et al.

In today's fast-paced world, stress has become a growing health concern. While more automatic stress tracking technologies have recently become available on wearable or mobile devices, there is still a limited understanding of how they are actually used in everyday life. This paper presents an empirical study of automatic stress-tracking technologies in use in China, based on semi-structured interviews with 17 users. The study highlights three challenges of stress-tracking data engagement that prevent effective technology usage: the lack of immediate awareness, the lack of pre-required knowledge, and the lack of corresponding communal support. Drawing on the stress-tracking practices uncovered in the study, we bring these issues to the fore, and unpack assumptions embedded in related works on self-tracking and how data engagement is approached. We end by calling for a reconsideration of data engagement as part of self-tracking practices with technologies rather than simply looking at the user interface.

Yue You, Xinning Gui

Recently, there has been a growing interest in developing AI-enabled chatbot-based symptom checker (CSC) apps in the healthcare market. CSC apps provide potential diagnoses for users and assist them with self-triaging based on Artificial Intelligence (AI) techniques using human-like conversations. Despite the popularity of such CSC apps, little research has been done to investigate their functionalities and user experiences. To do so, we conducted a feature review, a user review analysis, and an interview study. We found that the existing CSC apps lack the functions to support the whole diagnostic process of an offline medical visit. We also found that users perceive the current CSC apps to lack support for a comprehensive medical history, flexible symptom input, comprehensible questions, and diverse diseases and user groups. Based on these results, we derived implications for the future features and conversational design of CSC apps.

Yue You, Yubo Kou, Xianghua Ding et al.

Recently, consumer-facing health technologies such as Artificial Intelligence (AI)-based symptom checkers (AISCs) have sprung up in everyday healthcare practice. AISCs solicit symptom information from users and provide medical suggestions and possible diagnoses, a responsibility that people usually entrust with real-person authorities such as physicians and expert patients. Thus, the advent of AISCs begs a question of whether and how they transform the notion of medical authority in everyday healthcare practice. To answer this question, we conducted an interview study with thirty AISC users. We found that users assess the medical authority of AISCs using various factors including automated decisions and interaction design patterns of AISC apps, associations with established medical authorities like hospitals, and comparisons with other health technologies. We reveal how AISCs are used in healthcare delivery, discuss how AI transforms conventional understandings of medical authority, and derive implications for designing AI-enabled health technology.

Yubo Kou, Xinning Gui

Artificial intelligence (AI) has become prevalent in our everyday technologies and impacts both individuals and communities. The explainable AI (XAI) scholarship has explored the philosophical nature of explanation and technical explanations, which are usually driven by experts in lab settings and can be challenging for laypersons to understand. In addition, existing XAI research tends to focus on the individual level. Little is known about how people understand and explain AI-led decisions in the community context. Drawing from XAI and activity theory, a foundational HCI theory, we theorize how explanation is situated in a community's shared values, norms, knowledge, and practices, and how situated explanation mediates community-AI interaction. We then present a case study of AI-led moderation, where community members collectively develop explanations of AI-led decisions, most of which are automated punishments. Lastly, we discuss the implications of this framework at the intersection of CSCW, HCI, and XAI.