Reminiscence has been shown to provide benefits for older adults, but traditionally relies on personal photos as memory cues and interactions with real people who may not always be available. We present ReminiBuddy, a novel LLM-powered multi-agent conversational system, which allows older adults to engage with two distinct agents—one embodying an older identity and the other a younger identity—while using not only personal photos but also 3D models of generic nostalgic objects as memory cues. Our study, with older adult participants, found that the conversational approach both enjoyable and beneficial for reminiscence. While the younger agent was perceived as more emotionally engaging, the older one fostered greater resonance in content. Personal photos prompted autobiographical memories, whereas 3D generic nostalgic objects evoked shared memories of an era, contributing to a more multifaceted reminiscence experience. We further present design implications for better supporting older adults in reminiscing with LLM-powered conversational agents.
Human-Computer Interaction and Human-Robot Interaction researchers have developed various reminiscence technologies for older adults, but the focus of such work has mostly been on making the technology usable and improving older adults' memory recall. Our study of a robot facilitating reminiscence through conversations about personal photographs with 20 older adults uncovered a less discussed aspect of such interactions: reminiscence can evoke both \textit{bitter} and \textit{sweet} emotions. Without adequate emotional sensitivity, the robot sometimes responded inappropriately, requiring researchers to intervene in the interaction to address misunderstandings.
To understand how to better address these challenges, we conducted a follow-up co-design workshop with 7 older adults to explore how the robot could better support managing bittersweet emotions. Through reflexive thematic analysis of the two studies, this paper identifies factors that trigger bittersweet emotions during reminiscence with a robot and provides strategies for technology to manage these emotions during such interactions. This research highlights the importance of addressing emotional experiences in the design of reminiscence technology. It also raises ethical concerns about the emotional vulnerability of deploying one-on-one AI technologies for older adults.
With increasing social mobility and an aging society, more older adults in China are migrating to new cities, known as “older drifters”. Due to fewer social connections and cultural adaptation, they face negative emotions such as loneliness and depression. While reminiscence-based interventions have been used to improve older adults' psychological well-being, challenges such as the lack of tangible materials and limited social resources constrain the feasibility of traditional reminiscence approaches for older drifters. To address this challenge, we designed RemiHaven, a personalized reminiscence support tool based on a two-phase formative study. It integrates “In-Town” and “Out-of-Town” peer agents to enhance personalization, engagement, and emotional resonance in the reminiscence process powered by Multimodal Large Language Models (MLLMs). Our evaluations show RemiHaven's strengths in supporting reminiscence while identifying potential challenges. We conclude by offering insights for the future design of reminiscence support tools for older migrants.
In this paper, we introduce the concept of asocial technologies (e.g., online purchases), which digitize activities that traditionally would have been carried out in person (e.g., in-person shopping). We argue that using asocial technologies limits users' opportunities for face-to-face interactions, which can be particularly detrimental to older adults (65+) who are more prone to social isolation and loneliness. Analyzing longitudinal survey data from the U.S. National Health and Aging Trends Study (N = 1925), we identified the adverse effects of asocial technologies on older adults' well-being. Using a within-between-level analytical framework, we found that an increased use of asocial technologies in a given year is associated with higher levels of anxiety and depression, and lower levels of overall health experienced by older adults in the following year. This work highlights the negative consequences of asocial technology use, emphasizing the need for more systematic designs in digital innovations that target seniors.
Journaling plays a crucial role in managing chronic conditions by allowing patients to document symptoms and medication intake, providing essential data for long-term care. While valuable, traditional journaling methods often rely on static, self-directed entries, lacking interactive feedback and real-time guidance. This gap can result in incomplete or imprecise information, limiting its usefulness for effective treatment. To address this gap, we introduce PATRIKA, an AI-enabled prototype designed specifically for people with Parkinson's disease (PwPD). The system incorporates cooperative conversation principles, clinical interview simulations, and personalization to create a more effective and user-friendly journaling experience. Through two user studies with PwPD and iterative refinement of PATRIKA, we demonstrate conversational journaling's significant potential in patient engagement and collecting clinically valuable information. Our results showed that generating probing questions PATRIKA turned journaling into a bi-directional interaction. Additionally, we offer insights for designing journaling systems for healthcare and future directions for promoting sustained journaling.
Parkinson's Disease (PD) significantly impacts driving abilities, often leading to early driving cessation or accidents due to reduced motor control and increasing reaction times. To diminish the impact of these symptoms, we developed PANDA (Parkinson's Assistance and Notification Driving Aid), a multi-modality real-time alert system designed to monitor driving patterns continuously and provide immediate alerts for irregular driving behaviors, enhancing driver safety of individuals with PD. The system was developed through a participatory design process with 9 people with PD and 13 non-PD individuals using a driving simulator, which allowed us to identify critical design characteristics and collect detailed data on driving behavior. A user study involving individuals with PD evaluated the effectiveness of PANDA, exploring optimal strategies for delivering alerts and ensuring they are timely and helpful. Our findings demonstrate that PANDA has the potential to enhance the driving safety of individuals with PD, offering a valuable tool for maintaining independence and confidence behind the wheel.
Much research on older people with memory concerns is focused on tracking and informed by the priorities of others. In this paper, we seek to understand the potential that people with memory concerns see in tracking. We conducted interviews with 29 participants with concerns about their memory and engaged in an affective writing approach. We find a range of potentials that can be traced to how participants are already self-tracking. Emotions associated with these potentials vary: from acceptance to resistance, and positive anticipation to aversion. Participants are emotionally motivated to foreclose possibilities in some instances and keep them open in others. While individual and unique, potential is structured by forces that include individual routines, relationships with others, and macro-level institutions and cultural contexts. We reflect on these findings in the context of research on self-tracking with older adults, designing with ambiguity, and forces that structure the experience of living with memory concerns.