Large language models (LLMs) offer novel opportunities to support health behavior change, yet existing work has narrowly focused on text-only interactions. Building on decades of HCI research on effective behavior change interactions, we present Bloom, an application for physical activity promotion that integrates an LLM-based health coaching chatbot with existing design strategies and UI elements. As part of Bloom’s development, we conducted a redteaming evaluation and contribute a safety benchmark dataset. In a four-week randomized field study (N=54) comparing Bloom to a no-LLM control, we observed important shifts in psychological outcomes: participants in the LLM condition reported stronger beliefs that activity was beneficial, greater enjoyment, and more self-compassion. Both conditions significantly increased physical activity levels, doubling the proportion of participants meeting recommended weekly guidelines, though descriptively, we observed no advantage for the LLM condition in short-term physical activity levels. Instead, our findings suggest that LLMs may be more effective at shifting mindsets that precede longer-term behavior change.

It is often of interest to learn a context-sensitive decision policy, such as in contextual multi-armed bandit processes. To quantify the efficiency of a machine learning algorithm for such settings, probably approximately correct (PAC) bounds, which bound the number of samples required, or cumulative regret guarantees, are typically used. However, real-world settings often have limited resources for experimentation, and decisions/interventions may differ in the amount of resources required (e.g., money or time). Therefore, it is of interest to consider how to design an experiment strategy that reduces the experimental budget needed to learn a near-optimal contextual policy. Unlike reinforcement learning or bandit approaches that embed costs into the reward function, we focus on reducing resource use in learning a near-optimal policy without resource constraints. We introduce two resource-aware algorithms for the contextual bandit setting and prove their soundness. Simulations based on real-world datasets demonstrate that our algorithms significantly reduce the resources needed to learn a near-optimal decision policy compared to previous resource-unaware methods.

Work-nonwork balance is an important aspect of workplace well-being with associations to improved physical and mental health, job performance, and quality of life. However, realizing work-nonwork balance goals is challenging due to competing demands and limited resources within organizational and interpersonal contexts. These challenges are compounded by technologies that blur the boundaries of work and nonwork in the always-on work cultures. At an individual level, such challenges can be subsided through the effective application of self-regulation techniques, such as implementation intentions and mental contrasting (IIMC). Further supporting these techniques through reflection on personal data, we implement the idea of data-driven IIMC into a self-tracking and behavior planning system and evaluate it in a three-week between-participant study with 43 information workers who used our system for improving work-nonwork balance. We find evidence that reflection on personal data improves awareness of behavior plan compliance and rescheduling, which are important in realizing work-nonwork balance goals. We also observe the value of micro-reflection, reflection on limited data of the very recent past, for IIMC. Our findings highlight opportunities for automation in data collection and sense-making and for further exploring the role of data-driven IIMC as boundary negotiating artifacts in support of work-nonwork balance goals.

Voice-first ambient interfaces (VFAIs), such as Alexa, can uniquely meet the health needs of older adults. However, inequitable technology may worsen health disparities and decrease independence, calling for participatory methods to increase the agency of older adults in the design processes of these technologies. We adapt and conduct a participatory design workshop to focus on ambient interfaces for home health with 13 diverse older adults in San Francisco's Tenderloin neighborhood. Using the prototypes they made as discussion catalyzers, participants shared different perspectives entailing stigmatized topics that can be difficult to discuss, such as drug use, sex, isolation, and dementia. They deliberated on the negative implications of VFAIs, such as a justified concern for surveillance, in conjunction with their positive implications, such as receiving always-available ''non-judgmental'' support. Similarly, the risk of leaking drug use data was considered alongside the benefits of sharing important medical information with clinicians. We synthesize our findings into design considerations, such as how we might address varying levels of trust in different stakeholders and reduce stigma that may hinder users from fully benefiting from VFAIs' capabilities.

The rapid pace of technological progress carries with it a heightened risk of ethics and privacy violations, creating an urgent need for mechanisms to address this risk. We approach this problem from the perspective of designers and technologists aiming to design technology that better accounts for ethical implications. We iteratively developed a workshop-based method (N=113, seven workshops) for probing ethical implications of emerging ubiquitous computing technologies. We contribute a method that enables people with varying levels and areas of domain expertise and with a variety of lived experiences to collectively speculate about the ethical implications of emerging technologies, navigate value tensions, and prototype artifacts as a way to grapple with those tensions. We introduce implication design as a means for participants with and without design experience to communicate how a technology might change to better serve them. Lastly, we share our learnings from and reflections on our design process.

Reflection on one’s personal data can be an effective tool for supporting wellbeing. However, current wellbeing reflection support tools tend to offer a one-size-fits-all approach, ignoring the diversity of people’s wellbeing goals and their agency in the self-reflection process. In this work, we identify an opportunity to help people work toward their wellbeing goals by empowering them to reflect on their data on their own terms. Through a formative study, we inform the design and implementation of Pearl, a workplace wellbeing reflection support tool that allows users to explore their personal data in relation to their wellbeing goal. Pearl is a calendar-based interactive machine teaching system that allows users to visualize data sources and tag regions of interest on their calendar. In return, the system provides insights about these tags that can be saved to a reflection journal. We used Pearl as a technology probe with 12 participants without data science expertise and found that all participants successfully gained insights into their workplace wellbeing. In our analysis, we discuss how Pearl’s capabilities facilitate insights, the role of machine assistance in the self-reflection process, and the data sources that participants found most insightful. We conclude with design dimensions for intelligent reflection support systems as inspiration for future work.

Prior work has identified a resilient phenomenon that threatens the performance of human-AI decision-making teams: overreliance, when people agree with an AI, even when it is incorrect. Surprisingly, overreliance does not reduce when the AI produces explanations for its predictions, compared to only providing predictions. Some have argued that overreliance results from cognitive biases or uncalibrated trust, attributing overreliance to an inevitability of human cognition. By contrast, our paper argues that people strategically choose whether or not to engage with an AI explanation, demonstrating empirically that there are scenarios where AI explanations reduce overreliance. To achieve this, we formalize this strategic choice in a cost-benefit framework, where the costs and benefits of engaging with the task are weighed against the costs and benefits of relying on the AI. We manipulate the costs and benefits in a maze task, where participants collaborate with a simulated AI to find the exit of a maze. Through 5 studies (N = 731), we find that costs such as task difficulty (Study 1), explanation difficulty (Study 2, 3), and benefits such as monetary compensation (Study 4) affect overreliance. Finally, Study 5 adapts the Cognitive Effort Discounting paradigm to quantify the utility of different explanations, providing further support for our framework. Our results suggest that some of the null effects found in literature could be due in part to the explanation not sufficiently reducing the costs of verifying the AI's prediction.

Tacit knowledge is a type of knowledge often existing in one's subconscious or embodied in muscle memory. Such knowledge is pervasive in creative practices yet remains difficult to observe or codify. To better understand tacit knowledge, we introduce a design method that leverages time-series data (interaction logs, physical sensor, and biosignal data) to isolate unique actions and behaviors between groups of users. This method is enacted in Eluent, a tool that distills hundreds of hours of dense activity data using an activity segmentation algorithm into a codebook - a set of distinct, characteristic sequences that comprise an activity. The results are made visually parsable in a representation we term process chromatograms that aid with 1) highlighting distinct periods of activity in creative sessions, 2) identifying distinct groups of users, and 3) characterizing periods of activity. We demonstrate the value of our method through a study of tacit process within computational notebooks and discuss ways process chromatograms can act as a knowledge mining technique, an evaluation metric, and a design-informing visualization.