Benjamin Tag

Cognitive load monitoring is important for understanding human performance in safety-critical healthcare environments. However, existing approaches often rely on controlled laboratory settings or self-reported assessments that may not adequately capture cognitive load during real-world clinical activities. In this paper, we investigate multimodal physiological sensing for cognitive load prediction in nurses from a Surgical Intensive Care Unit (SICU) performing routine clinical tasks. We collect and analyze electroencephalography (EEG), electrodermal activity (EDA), and blood volume pulse (BVP) signals from 20 nurses in semi-controlled field environments. Using leave-one-subject-out cross-validation, we systematically evaluate the influence of temporal window size, sensing modality, and machine learning models on cognitive load prediction performance. Our results show that longer temporal windows consistently improve prediction performance across sensing modalities, with a 30s multimodal configuration achieving the highest overall performance (76.4% accuracy). Among individual modalities, EDA achieved performance comparable to the multimodal configuration, while EEG and BVP features contributed complementary cortical and cardiovascular information, supporting the feasibility of wearable physiological sensing in semi-controlled clinical environments. Overall, this work demonstrates the potential of wearable physiological sensing for practical and interpretable cognitive load monitoring in healthcare settings.

As legal professionals increasingly incorporate artificial intelligence into their daily work, established professional norms of reasoning, expertise, and ethical behaviour are being challenged. Generative AI (GenAI) tools are being rapidly adopted by legal professionals across many jurisdictions. Although these technologies offer significant potential benefits, concerns persist that they may degrade professional skills. Misuse also poses risks to legal professionalism and to the broader justice system. This workshop brings together legal professionals, researchers, and experts in AI and computing to discuss how GenAI tools may be designed so legal professionals develop skills to productively use artificial intelligence; and how we might guard against deskilling and cognitive offloading in high-stakes work. Our workshop will enable researchers working in this emerging yet contentious area to share findings, receive feedback, and propose new research and design ideas, contributing to a shared research agenda for future work on augmented legal practice.

Virtual reality has been effectively used for eliciting emotions, yet most research focuses on the intensity of affective responses rather than on how interaction influences those experiences. To address this gap, we advance a validated VR emotion-elicitation dataset through two key extensions. First, we add a new high-arousal, high-valence scene and validate its effectiveness in a within-subject study (N=24). Second, we incorporate interactive elements into each scene, creating both interactive and non-interactive versions to examine the impact of interaction on emotional responses. We evaluate interaction through a multimodal approach combining subjective ratings and physiological signals to capture both conscious and unconscious affective responses. Our evaluation study (N=84) shows that interaction not only amplifies emotions but modulates them in context, supporting coping in negative scenes and enhancing enjoyment in positive scenes. These findings highlight the potential of scene-tailored interaction for different applications, where regulating emotions is as important as eliciting them.

Integrating physiological signals in Human-Computer Interaction research has significantly advanced our understanding of user experiences and interactions. However, the interdisciplinary nature of this research presents numerous technical challenges. These include the lack of standardized protocols, unclear guidelines for data collection and preprocessing, and difficulties in pipeline management, reproducibility, and transparency. The purpose of this meet-up is to offer a lightweight opportunity for CHI attendees to connect around these issues, exchange experiences, share tools and workflows, and identify best practices. By fostering open exchange, we aim to improve the reliability of physiological data in HCI, promote open science, and build a sustainable community. Ultimately, our goal is to overcome technical barriers and strengthen the foundation for future research in physiological computing.

Eye strain presents a significant challenge in human-information interaction in virtual reality (VR), as prolonged exposure contributes to various eye problems. This study introduces a new gaze redirection method called EyeXRciser, which passively activates eye movements to help prevent eye muscle stiffness during VR reading. This method achieves gaze redirection by slowly shifting the relative position of the text window within the user’s field of view through a head-bound coordinate system. We implemented our method with two different redirection speeds (i.e., unnoticeable speed at 0.03 rad/s; noticeable speed at 0.12 rad/s) and conducted a user study (N = 24) comparing with a baseline using a fixed text window. Results show that both our methods successfully minimized the decline in accommodative ability caused by prolonged reading, without negatively impacting reading comprehension. Results also show that the unnoticeable redirection speed produced less subjective discomfort, eye fatigue, and reading distraction than the noticeable speed.

Conversational AI now helps people perform a plethora of everyday tasks, especially online. Such cognitive offloading can enhance task performance, but does not always contribute to the development of the underlying human abilities. As a result, there are increasing concerns about the potential deleterious effects of overusing AI in one’s work. This workshop explores a timely and positive framing: cognitive augmentation, where conversational AI can help people grow rather than just perform their tasks. We bring together a diverse set of researchers to work on how these systems might foster inherently human cognitive capabilities, such as meta-cognition, self-motivation, and emotional intelligence, without creating dependency.