arXiv subjects

Joy Lai

Publications and source records attributed to Joy Lai.

4 recordsLinked to original sources

arXiv2026

Remindful: Designing Reminder Systems for Caregiver Interpretation in Dementia Care

Digital reminder systems are widely used in dementia care to support everyday tasks, but they are typically designed for one-way prompting rather than helping caregivers interpret engagement over time. We present Remindful, a caregiver-informed reminder platform that extends task prompting with caregiver-facing alerts, summaries, and review features to support awareness in home-based dementia care. Drawing on formative caregiver interviews, lived-experience advisor input, and in-home deployments with two caregiver-PLwD dyads, we examine how reminder-based caregiver awareness functions in practice. Our findings show that reminder systems can support caregiver reassurance, household coordination, and awareness of routines over time, but that reminder interaction data is highly context-dependent. Household participation, prompt attribution, routine mismatch, accessibility barriers, and technical failures all shaped what reminder logs could reasonably mean. We argue that reminder systems should not be treated as neutral behavioral sensors, but designed as assistive infrastructures for caregiver interpretation that preserve uncertainty and support contextual sensemaking in real homes.

cs.HC↗

arXiv2026

Listening before Asking: Lived-Experience Advisors as Methodological Partners in Dementia Caregiving Studies

Research with dementia caregivers poses persistent methodological and ethical challenges, particularly when interview-based studies are designed without sufficient grounding in lived caregiving realities. Questions framed through clinical or deficit-oriented assumptions risk alienating participants, undermining rapport, and producing shallow or ethically fraught data. While human-computer interaction (HCI) research increasingly adopts participatory approaches in technology design, participation rarely extends to the design of research methods themselves. This paper examines the role of lived-experience advisors as methodological partners in caregiver interview research. We report on a qualitative study in which two advisors with extensive dementia caregiving experience were engaged prior to fieldwork as methodological partners, extending participatory principles beyond technology design into the design of research methods themselves. Drawing on transcripts of advisor consultations and subsequent interviews with ten caregivers and one person living with dementia, we identify two key methodological contributions of advisor involvement. First, advisors enabled anticipatory validity by surfacing caregiving challenges, ethical sensitivities, and interpretive concerns that later appeared in caregiver interviews, allowing the researcher to enter the field with grounded awareness under constrained recruitment and fieldwork conditions. Second, advisors provided cultural, emotional, and systemic context that improved interpretive sensitivity and helped avoid misreadings. We argue that lived experience functions as methodological infrastructure, extending participatory principles into the design and conduct of research itself, and constituting a generalizable methodological pattern for HCI research with caregivers and other vulnerable or marginalized populations.

cs.HC↗

arXiv2025

PersonaDrift: A Benchmark for Temporal Anomaly Detection in Language-Based Dementia Monitoring

People living with dementia (PLwD) often show gradual shifts in how they communicate, becoming less expressive, more repetitive, or drifting off-topic in subtle ways. While caregivers may notice these changes informally, most computational tools are not designed to track such behavioral drift over time. This paper introduces PersonaDrift, a synthetic benchmark designed to evaluate machine learning and statistical methods for detecting progressive changes in daily communication, focusing on user responses to a digital reminder system. PersonaDrift simulates 60-day interaction logs for synthetic users modeled after real PLwD, based on interviews with caregivers. These caregiver-informed personas vary in tone, modality, and communication habits, enabling realistic diversity in behavior. The benchmark focuses on two forms of longitudinal change that caregivers highlighted as particularly salient: flattened sentiment (reduced emotional tone and verbosity) and off-topic replies (semantic drift). These changes are injected progressively at different rates to emulate naturalistic cognitive trajectories, and the framework is designed to be extensible to additional behaviors in future use cases. To explore this novel application space, we evaluate several anomaly detection approaches, unsupervised statistical methods (CUSUM, EWMA, One-Class SVM), sequence models using contextual embeddings (GRU + BERT), and supervised classifiers in both generalized and personalized settings. Preliminary results show that flattened sentiment can often be detected with simple statistical models in users with low baseline variability, while detecting semantic drift requires temporal modeling and personalized baselines. Across both tasks, personalized classifiers consistently outperform generalized ones, highlighting the importance of individual behavioral context.

cs.AI↗

arXiv2025

From Checking to Sensemaking: A Caregiver-in-the-Loop Framework for AI-Assisted Task Verification in Dementia Care

Informal caregivers play a central role in enabling people living with dementia (PLwD) to remain at home, yet they face persistent challenges verifying whether daily tasks have been completed. Existing digital reminder systems prompt actions but rarely confirm outcomes, leaving caregivers to double-check tasks manually. This study explores how generative artificial intelligence (AI) might support caregiver-led task verification without displacing human judgment. We combined qualitative interviews with ten caregivers and one PLwD with a speculative simulation probe using a generative large language model to generate follow-up questions and flag responses for verification. Using template analysis, we identified three interrelated patterns of reasoning: detecting anomalies, constructing trustworthy evidence, and calibrating trust and control. These insights informed the Caregiver-in-the-Loop Task Verification (CLTV) framework, which models verification as a collaborative cycle of anomaly detection, evidence triangulation, AI-assisted summarization, and accountability circulation centered on caregiver oversight. CLTV advances human-AI collaboration theory by situating interpretability, trust, and control within the relational and emotional realities of dementia care and by offering design principles for transparent, adjustable, and context-aware AI support. We contribute a care-centered extension of human-AI collaboration theory, demonstrating how interpretability and trust can be operationalized through caregiver oversight.

cs.HC↗