Artificial Intelligence (AI) is increasingly integrated into Building Automation Systems (BAS) to enhance energy efficiency and occupant comfort. Yet, rather than functioning as neutral optimization tools, AI in BAS operates within fragile infrastructures, limited resources, and institutional politics. We present a qualitative study of 23 interviews with energy professionals, AI researchers, and student representatives at the University of Toronto, an institution recognized for its sustainability leadership. Participants expressed ambivalence: AI was valued for forecasting and optimization, yet concerns arose around legitimacy, labor demands, and environmental paradoxes. Fairness in occupant comfort was highlighted, not as an inherent property of models but as a situated practice shaped by infrastructural governance negotiated across roles and inequities. Communication also emerged as a form of occupant agency, where human, machine, and AI-mediated dialogue makes automated decisions legible and contestable. These findings reframe AI in BAS as socio-technical infrastructure and inform our design recommendations for transparent, participatory, and just systems.

Human social interactions occur in group settings of varying sizes and locations, depending on the type of social activity. The ability to distinguish group formations based on their purposes transforms how group detection mechanisms function. Not only should such tools support the effective detection of serendipitous encounters, but they can derive categories of relation types among users. Determining who is involved, what activity is performed, and when and where the activity occurs are critical to understanding group processes in greater depth, including supporting goal-oriented applications (e.g., performance, productivity, and mental health) that require sensing social factors. In this work, we propose W4-Groups that captures the functional perspective of variability and repeatability when automatically constructing short-term and long-term groups via multiple data sources (e.g., WiFi and location check-in data). We design and implement W4-Groups to detect and extract all four group features who-what-when-where from the user's daily mobility patterns. We empirically evaluate the framework using two real-world WiFi datasets and a location check-in dataset, yielding an average of 92% overall accuracy, 96% precision, and 94% recall. Further, we supplement two case studies to demonstrate the application of W4-Groups for next-group activity prediction and analyzing changes in group behavior at a longitudinal scale, exemplifying short-term and long-term occurrences.

Digital contact tracing can limit the spread of infectious diseases. Nevertheless, barriers remain to attain sufficient adoption. In this study, we investigate how willingness to participate in contact tracing is affected by two critical factors: the modes of data collection and the type of data collected. We conducted a scenario-based survey study among 220 respondents in the United States (U.S.) to understand their perceptions about contact tracing associated with automated and manual contact tracing methods. The findings indicate a promising use of smartphones and a combination of public health officials and medical health records as information sources. Through a quantitative analysis, we describe how different modalities and individual demographic factors may affect user compliance when participants are asked to provide four key information pieces for contact tracing.

Social identification: how much individuals psychologically associate themselves with a group has been posited as an essential construct to measure individual and group dynamics. Studies have shown that individuals who identify very differently from their workgroup provide critical cues to the lack of social support or work overloads. However, measuring identification is typically achieved through time-consuming and privacy-invasive surveys. We hypothesize that the extremities in-group norm affects individuals' behaviors, thus more likely to give rise to negative appraisals. As a more convenient and less-invasive technique, we propose a method to predict individuals who are increasingly different in identifying themselves with their working peers using mobility data passively sensed from the WiFi infrastructure. To test our hypothesis, we collected WiFi data of 62 college students over a whole semester. Students provided regular self-reports on their identification towards a workgroup as ground truth. We analyze the contrasts between groups' mobility patterns and build a classification model to determine students who identify very differently from their workgroup. The classifier achieves approximately 80% True Positive Rate (TPR), 73% True negative rate (TNR), and 78% Accuracy (ACC). Such a mechanism can help distinguish students who are more likely to struggle with negative workgroup appraisals and enable interventions to improve their overall team experience.

Much research argues that feeling overwhelmed by stress and for prolonged periods can lead to severe mental illness such as early onset depression and anxiety among many others. Recovering from severe stress to a normal state is much easier, in terms of the length of time and treatment required, compared to when more serious conditions have manifested [1]. Unfortunately, existing stress monitoring applications either require dedicated applications to be installed on the user's mobile device or use various mobile and wearable sensors [2, 4, 6, 7]; thus are not scalable to large number of users. Our goal is to provide a community-wide "safety net" that will automatically and non-intrusively detect individuals exhibiting signs of excessive stress without them installing any dedicated app. YouTube Demo Link https://youtu.be/LKQvIX4W6L0

Stress and depression are a common affliction in all walks of life. When left unmanaged, stress can inhibit productivity or cause depression. Depression can occur independently of stress. There has been a sharp rise in mobile health initiatives to monitor stress and depression. However, these initiatives usually require users to install dedicated apps or multiple sensors, making such solutions hard to scale. Moreover, they emphasise sensing individual factors and overlook social interactions, which plays a significant role in influencing stress and depression while being a part of a social system. We present StressMon, a stress and depression detection system that leverages single-attribute location data, passively sensed from the WiFi infrastructure. Using the location data, it extracts a detailed set of movement, and physical group interaction pattern features without requiring explicit user actions or software installation on client devices. These features are used in two different machine learning models to detect stress and depression. To validate StressMon, we conducted three different longitudinal studies at a university with different groups of students, totalling up to 108 participants. Our evaluation demonstrated StressMon detecting severely stressed students with a 96.01% True Positive Rate (TPR), an 80.76% True Negative Rate (TNR), and a 0.97 area under the ROC curve (AUC) score (a score of 1 indicates a perfect binary classifier) using a 6-day prediction window. In addition, StressMon was able to detect depression at 91.21% TPR, 66.71% TNR, and 0.88 AUC using a 15-day window. We end by discussing how StressMon can expand CSCW research, especially in areas involving collaborative practices for mental health management.

Problem behaviors are particularly common in children with neurodevelopmental disorders like Autism and Down syndrome. These behaviors sometimes discourage social inclusion, inhibit learning development, and cause severe injuries, but caregivers are often unable to attend to their children immediately when the behaviors occur. Recent research shows that problem behavior can be automatically detected with wearable devices, but it is still not clear how to reduce caregivers' burdens and facilitate academic, social, and functional development of children with problem behaviors. We conducted a field study at a school with 21 children who exhibit problem behaviors and found that they needed frequent interventions in the form of visual cue cards and verbal reminders. We then developed a proof-of-concept that uses smart watch notifications to help children control their behavior without intervention from caregivers. A preliminary evaluation indicates that notifications modeled after teachers' current intervention strategies can help children control their problem behaviors.