The home environment plays a critical role in shaping daily routines that influence emotional wellbeing. While previous research has leveraged mobile and wearable devices to track emotional wellbeing indicators, these approaches often suffer from limited adherence and data gaps when users are not actively engaged. To address this, we further explore home IoT sensing as a passive and unobtrusive modality for monitoring emotional wellbeing. We conducted a four-week user study (N=20), collecting data from mobile devices, wearables, and home IoT sensors. Our quantitative analysis showed that incorporating home IoT data better captured associations between domestic routines and emotional wellbeing than mobile and wearable data alone. However, domestic activity patterns varied significantly across participants, highlighting the personalized nature of domestic routines. To further investigate these differences, we developed an informatics tool for participants to visualize and reflect on their behavioral data. Semi-structured interviews revealed that participants found home IoT data intuitive and insightful in understanding their emotional wellbeing, leading to a positive shift in privacy concerns. Our findings highlight home IoT sensing as a promising tool for tracking emotional wellbeing and provide design implications for future sensor-enabled home healthcare services.
The text-based emoji search, despite its widespread use and extensive variety of emojis, has received limited attention in terms of understanding user challenges and identifying ways to support users. In our formative study, we found the bottlenecks in text-based emoji searches, focusing on challenges in finding appropriate search keywords and user modification strategies for unsatisfying searches. Building on these findings, we introduce MOJI, an emoji entry system supporting 1) query expansion with content-relevant multi-dimensional keywords reflecting users’ modification strategies and 2) emoji recommendations that belong to each search query. The comparison study demonstrated that our system reduced the time required to finalize search keywords compared to traditional text-based methods. Additionally, users achieved higher satisfaction in final emoji selections through easy attempts and modifications on search queries, without increasing the overall selection time. We also present a comparison of emoji suggestion algorithms (GPT and iOS) to support query expansion.
16 October 2025 in Proceedings of the ACM on Human-Computer Interaction
The growing demand for mental health support has highlighted the limitations of traditional counseling accessibility, increasing the usage of digital mental health interventions. There has been a rising interest in using robots to support mental health due to their benefits in engagement and rapport. Capitalizing on the opportunity of placemaking for designing a feasible robotic digital mental health intervention, our study explores the Robot Counseling Center (RCC) and its robotic counselor, Cumpa, designed to improve mental health accessibility and user engagement. A two-week field study with 20 participants evaluated RCC's impact on their mental health, engagement, and sense of place within a counseling environment. Results indicate that RCC positively influences emotional awareness and engagement. Our findings provide insights into the role of social robots in mental health interventions and offer design implications for developing robotic counseling centers as supportive, effective spaces, contributing to building better places and interactive systems.