The importance of empathy cannot be overstated in modern societies where people of diverse backgrounds increasingly interact together. The HCI community has strived to foster affective empathy through immersive technologies. Many previous techniques are built upon a premise that presenting the same experience as-is may help evoke the same emotion, which however faces limitations in matters where the emotional responses largely differ across individuals.
In this paper, we present a novel concept of generating a personalized experience based on a large language model (LLM) to facilitate affective empathy between individuals despite their differences. As a case study to showcase its effectiveness, we developed EmoSync, an LLM-based agent that generates personalized analogical microaggression situations, facilitating users to personally resonate with a specific microaggression situation of another person. EmoSync is designed and evaluated along a 3-phased user study with 100+ participants. We comprehensively discuss implications, limitations, and possible applications.
Frontline workers (FLWs) in gender-based violence (GBV) service provision regularly engage in intense emotional labor to provide survivors of GBV with essential, often life-saving, services. However, FLWs experience intense burnout, resulting in turnover rates as high as 50% annually and a critical loss of services for survivors. In order to design digital burnout interventions in a context where so few exist, we recruited 15 FLWs for a 3-stage qualitative study where they used two existing applications to reflect on, and reimagine, concrete design features necessary to address FLW burnout in GBV service provision. We contribute important findings regarding designing specifically for empathy-based stress (EBS) in frontline work contexts, preferences for activities, desired interactivity, among other requirements for interventions. We synthesize our design recommendations through an example scenario of a collaborative just-in-time adaptive intervention (co-JITAI) system that integrates peer-based support that can adapt to users’ changing needs and contexts over time.
Parents of children in speech therapy play a crucial role in delivering consistent, high-quality home practice, which is essential for helping children generalize new speech skills to everyday situations. However, this responsibility is often complicated by uncertainties in implementing therapy techniques and keeping children engaged. In this study, we explore how varying levels of AI oversight can provide informational, emotional, and practical support to parents during home speech therapy practice. Through semi-structured interviews with 20 parents, we identified key challenges they face and their ideas for AI assistance. Using these insights, we developed six design concepts, which were then evaluated by 20 Speech-Language Pathologists (SLPs) for their potential impact, usability, and alignment with therapy goals. Our findings contribute to the discourse on AI’s role in supporting therapeutic practices, offering design considerations that address the needs and values of both families and professionals.
HCI research on goals and behavior change has significantly increased over the past decade. However, while emerging work has synthesized personal informatics goals, fewer efforts have focused on also integrating HCI research on behavior change to chart future research directions.We conducted a systematic reviewof 180 papers focused on goals and behavior change from over 10 years of SIGCHI journals and conference proceedings. We further analyzed 37 papers from the data set that included evaluations of interventions’ effectiveness in-the-wild. We also reported on the effectiveness of 76 of such technology-based interventions and the meta-analysis of 28 of these interventions. We find that most research has focused on goals in the health and wellbeing domains, centered on the individual, low intrinsic goals, and partial use of theoretical constructs in technology-based interventions. We highlight opportunities for supporting multiple-domain, social, high intrinsic, and qualitative goals in HCI research for behavior change, and for more effective technology-based interventions with stronger theoretical underpinning, supporting users’ awareness of deep motives for qualitative goals.
Over the past decades, numerous concepts and prototypes for fostering emotional connections across distance (relatedness technologies) have been proposed. This has made it challenging for researchers and designers in Human-Computer Interaction (HCI) to maintain a comprehensive overview and effectively build on previous work. To address this, we conducted a systematic literature search (PRISMA) and collected 241 concepts and prototypes (2010-2024). We organized this corpus according to key aspects: (1) target population, (2) theoretical grounding, (3) design, (4) evaluation, and (5) ethics. Based on this, we developed the “COmpendium of RElatedness Technologies” (CORE), an open-access, searchable online database that provides researchers and practitioners with a reliable repository to inform future work. In addition, we present a systematic review of the corpus, revealing that despite its long tradition work on relatedness technologies remains characterized by limited theoretical grounding, lack of robust empirical evidence of effects, and insufficient attention to ethical considerations.
Desk workers may often experience more negative than positive emotions in office settings, making emotion regulation (ER) crucial for their mental health. Squeezable interfaces have shown the potential to reduce anxiety and stress in digital and non-digital ER. However, few studies have explored how they can be leveraged to provide tangible and embodied support for workplace ER.
We interviewed five mental health experts and 16 desk workers and conducted five co-design workshops with 17 desk workers, aiming to understand how validated practices can be integrated into squeezable interfaces and how they should be designed to support ER and accommodate diverse needs in the context of the workplace. This study contributes to digital ER by identifying design opportunities for squeezable interfaces and by outlining design considerations and challenges for tangible and embodied interactions in ER support within the workplace.
Personalized support is essential to fulfill individuals’ emotional needs and sustain their mental well-being. Large language models (LLMs), with great customization flexibility, hold promises to enable individuals to create their own emotional support agents. In this work, we developed ChatLab, where users could construct LLM-powered chatbots with additional interaction features including voices and avatars. Using a Research through Design approach, we conducted a week-long field study followed by interviews and design activities (N = 22), which uncovered how participants created diverse chatbot personas for emotional reliance, confronting stressors, connecting to intellectual discourse, reflecting mirrored selves, etc. We found that participants actively enriched the personas they constructed, shaping the dynamics between themselves and the chatbot to foster open and honest conversations. They also suggested other customizable features, such as integrating online activities and adjustable memory settings. Based on these findings, we discuss opportunities for enhancing personalized emotional support through emerging AI technologies.