Anind K. Dey

Xuhai Xu, Han Zhang, Yasaman Sefidgar et al. · uw

Recent research has demonstrated the capability of behavior signals captured by smartphones and wearables for longitudinal behavior modeling. However, there is a lack of a comprehensive public dataset that serves as an open testbed for fair comparison among algorithms. Moreover, prior studies mainly evaluate algorithms using data from a single population within a short period, without measuring the cross-dataset generalizability of these algorithms. We present the first multi-year passive sensing datasets, containing over 700 user-years and 497 unique users' data collected from mobile and wearable sensors, together with a wide range of well-being metrics. Our datasets can support multiple cross-dataset evaluations of behavior modeling algorithms' generalizability across different users and years. As a starting point, we provide the benchmark results of 18 algorithms on the task of depression detection. Our results indicate that both prior depression detection algorithms and domain generalization techniques show potential but need further research to achieve adequate cross-dataset generalizability. We envision our multi-year datasets can support the ML community in developing generalizable longitudinal behavior modeling algorithms.

Xuhai Xu, Bingsheng Yao, Yuanzhe Dong et al.

Advances in large language models (LLMs) have empowered a variety of applications. However, there is still a significant gap in research when it comes to understanding and enhancing the capabilities of LLMs in the field of mental health. In this work, we present a comprehensive evaluation of multiple LLMs on various mental health prediction tasks via online text data, including Alpaca, Alpaca-LoRA, FLAN-T5, GPT-3.5, and GPT-4. We conduct a broad range of experiments, covering zero-shot prompting, few-shot prompting, and instruction fine-tuning. The results indicate a promising yet limited performance of LLMs with zero-shot and few-shot prompt designs for mental health tasks. More importantly, our experiments show that instruction finetuning can significantly boost the performance of LLMs for all tasks simultaneously. Our best-finetuned models, Mental-Alpaca and Mental-FLAN-T5, outperform the best prompt design of GPT-3.5 (25 and 15 times bigger) by 10.9% on balanced accuracy and the best of GPT-4 (250 and 150 times bigger) by 4.8%. They further perform on par with the state-of-the-art task-specific language model. We also conduct an exploratory case study on LLMs' capability on mental health reasoning tasks, illustrating the promising capability of certain models such as GPT-4. We summarize our findings into a set of action guidelines for potential methods to enhance LLMs' capability for mental health tasks. Meanwhile, we also emphasize the important limitations before achieving deployability in real-world mental health settings, such as known racial and gender bias. We highlight the important ethical risks accompanying this line of research.

Joshua Gluck, Christian Koehler, Jennifer Mankoff et al.

Heating, Ventilation, and Cooling (HVAC) systems are often the most significant contributor to the energy usage, and the operational cost, of large office buildings. Therefore, to understand the various factors affecting the energy usage, and to optimize the operational efficiency of building HVAC systems, energy analysts and architects often create simulations (e.g., EnergyPlus or DOE-2), of buildings prior to construction or renovation to determine energy savings and quantify the Return-on-Investment (ROI). While useful, these simulations usually use static HVAC control strategies such as lowering room temperature at night, or reactive control based on simulated room occupancy. Recently, advances have been made in HVAC control algorithms that predict room occupancy. However, these algorithms depend on costly sensor installations and the tradeoffs between predictive accuracy, energy savings, comfort and expenses are not well understood. Current simulation frameworks do not support easy analysis of these tradeoffs. Our contribution is a simulation framework that can be used to explore this design space by generating objective estimates of the energy savings and occupant comfort for different levels of HVAC prediction and control performance. We validate our framework on a real-world occupancy dataset spanning 6 months for 235 rooms in a large university office building. Using the gold standard of energy use modeling and simulation (Revit and Energy Plus), we compare the energy consumption and occupant comfort in 29 independent simulations that explore our parameter space. Our results highlight a number of potentially useful tradeoffs with respect to energy savings, comfort, and algorithmic performance among predictive, reactive, and static schedules, for a stakeholder of our building.

Adiba Orzikulova, Han Xiao, Zhipeng Li et al.

Despite a rich history of investigating smartphone overuse intervention techniques, AI-based just-in-time adaptive intervention (JITAI) methods for overuse reduction are lacking. We develop Time2Stop, an intelligent, adaptive, and explainable JITAI system that leverages machine learning to identify optimal intervention timings, introduces interventions with transparent AI explanations, and collects user feedback to establish a human-AI loop and adapt the intervention model over time. We conducted an 8-week field experiment (N=71) to evaluate the effectiveness of both the adaptation and explanation aspects of Time2Stop. Our results indicate that our adaptive models significantly outperform the baseline methods on intervention accuracy (>32.8\% relatively) and receptivity (>8.0\%). In addition, incorporating explanations further enhances the effectiveness by 53.8\% and 11.4\% on accuracy and receptivity, respectively. Moreover, Time2Stop significantly reduces overuse, decreasing app visit frequency by 7.0$\sim$8.9\%. Our subjective data also echoed these quantitative measures. Participants preferred the adaptive interventions and rated the system highly on intervention time accuracy, effectiveness, and level of trust. We envision our work can inspire future research on JITAI systems with a human-AI loop to evolve with users.

Anthony Wise, Xinyi Zhou, Martin Reimann et al.

Similar to social media bots that shape public opinion, healthcare and financial decisions, LLM-based ChatBots like ChatGPT can persuade users to alter their behavior. Unlike prior work that persuades via overt-partisan bias or misinformation, we test whether framing alone suffices. We conducted a crowdsourced study, where 336 participants interacted with a neutral or one of two value-framed ChatBots while deciding to alter US defense spending. In this single policy domain with controlled content, participants exposed to value-framed ChatBots significantly changed their budget choices relative to the neutral control. When the frame misaligned with their values, some participants reinforced their original preference, revealing a potentially replicable backfire effect, originally considered rare in the literature. These findings suggest that value-framing alone lowers the barrier for manipulative uses of LLMs, revealing risks distinct from overt bias or misinformation, and clarifying risks to countering misinformation.

Subigya K. Nepal, Gonzalo J. Martinez, Arvind Pillai et al.

The modern workplace is undergoing a radical transformation, driven by technological advances that blur the boundaries between human capability and digital augmentation. At the forefront of this evolution is passive sensing technology - a suite of tools that quietly monitor and interpret human behavior without active user engagement. This paper examines how these technologies are reshaping our understanding of workplace dynamics, with a particular focus on employee wellbeing and productivity. Through a comprehensive review of recent research, we explore both the transformative potential and inherent challenges of passive sensing in professional environments. Our analysis reveals emerging patterns in how these technologies can support worker health and performance, while also highlighting critical gaps in current research and opportunities for future innovation. We conclude by outlining a roadmap for integrating passive sensing into future workplaces in ways that enhance human potential while preserving dignity and autonomy.

Yasaman S. Sefidgar, Paula S. Nurius, Amanda Baughan et al.

Perceived discrimination is common and consequential. Yet, little support is available to ease handling of these experiences. Addressing this gap, we report on a need-finding study to guide us in identifying relevant technologies and their requirements. Specifically, we examined unfolding experiences of perceived discrimination among college students and found factors to address in providing meaningful support. We used semi-structured retrospective interviews with 14 students to understand their perceptions, emotions, and coping in response to discriminatory behaviors within the prior ten-week period. These 14 students were among 90 who provided experience sampling reports of unfair treatment over the same ten-week period. We found that discrimination is more distressing if students face related academic and social struggles or when the incident triggers beliefs of inefficacy. We additionally identified patterns of effective coping. By grounding the findings in an extended stress processing framework, we offer a principled approach to intervention design, which we illustrate through incident-specific and proactive intervention paradigms.

Momin M. Malik, Afsaneh Doryab, Michael Merrill et al.

We present a study to detect friendship, its strength, and its change from smartphone location data collectedamong members of a fraternity. We extract a rich set of co-location features and build classifiers that detectfriendships and close friendship at 30% above a random baseline. We design cross-validation schema to testour model performance in specific application settings, finding it robust to seeing new dyads and to temporalvariance.

Han Zhang, Paula Nurius, Yasaman Sefidgar et al.

The impact of COVID-19 on students has been enormous, with an increase in worries about fiscal and physical health, a rapid shift to online learning, and increased isolation. In addition to these changes, students with disabilities/health concerns may face accessibility problems with online learning or communication tools, and their stress may be compounded by additional risks such as financial stress or pre-existing conditions. To our knowledge, no one has looked specifically at the impact of COVID-19 on students with disabilities/health concerns. In this paper, we present data from a survey of 147 students with and without disabilities collected in late March to early April of 2020 to assess the impact of COVID-19 on these students' education and mental health. Our findings show that students with disabilities/health concerns were more concerned about classes going online than their peers without disabilities. In addition, students with disabilities/health concerns also reported that they have experienced more COVID-19 related adversities compared to their peers without disabilities/health concerns. We argue that students with disabilities/health concerns in higher education need confidence in the accessibility of the online learning tools that are becoming increasingly prevalent in higher education not only because of COVID-19 but also more generally. In addition, educational technologies will be more accessible if they consider the learning context, and are designed to provide a supportive, calm, and connecting learning environment.

Afsaneh Doryab, Prerna Chikarsel, Xinwen Liu et al.

The rich set of sensors in smartphones and wearable devices provides the possibility to passively collect streams of data in the wild. The raw data streams, however, can rarely be directly used in the modeling pipeline. We provide a generic framework that can process raw data streams and extract useful features related to non-verbal human behavior. This framework can be used by researchers in the field who are interested in processing data from smartphones and Wearable devices.

Brian D. Ziebart, Anind K. Dey, J Andrew Bagnell

Dealing with uncertainty in Bayesian Network structures using maximum a posteriori (MAP) estimation or Bayesian Model Averaging (BMA) is often intractable due to the superexponential number of possible directed, acyclic graphs. When the prior is decomposable, two classes of graphs where efficient learning can take place are tree structures, and fixed-orderings with limited in-degree. We show how MAP estimates and BMA for selectively conditioned forests (SCF), a combination of these two classes, can be computed efficiently for ordered sets of variables. We apply SCFs to temporal data to learn Dynamic Bayesian Networks having an intra-timestep forest and inter-timestep limited in-degree structure, improving model accuracy over DBNs without the combination of structures. We also apply SCFs to Bayes Net classification to learn selective forest augmented Naive Bayes classifiers. We argue that the built-in feature selection of selective augmented Bayes classifiers makes them preferable to similar non-selective classifiers based on empirical evidence.