EMBODIED CONVERSATIONAL AGENTS: TECHNOLOGIES TO SUPPORT OLDER ADULTS WITH MILD COGNITIVE IMPAIRMENT
Bibliographic record
Abstract
Various information technology applications with anthropomorphic or animal features (in order to generate likeness to a human or pet) have emerged, referred to as embodied conversational agents (ECAs), with the goal to engage older adults in conversations, with the ultimate goal to deliver health coaching, reminders, reminiscence therapy and address isolation and loneliness. We present findings from a longitudinal feasibility study assessing a digital companion system for ten older adults (average age 78.3 years) with mild cognitive impairment. The system was a tablet-based digital pet avatar that included features such as conversation ability, use of pictures and other media, and reminders. Participants used the system daily for 3 months and scored higher at the end of the study in cognition and social support scales (measured with the Montreal Cognitive Assessment and the MOS-Social support), with the largest benefit seen, as hypothesized, in the positive social interaction subscale. Participants scored lower in presence of depressive symptoms after study completion as assessed by the Patient Health Questionnaire PHQ-9. Interviews demonstrated that participants saw value in interacting with the system. Many appreciated the pet-like features and felt they developed attachment to it over time. Concerns included technical issues related to Internet connectivity and the repetitive nature of conversations. Our findings informed the creation of design recommendations for ECAs to support aging. We specifically focus on usability, responsiveness, ways to effectively engage clinicians and family members, as well as highlight ethical issues stemming from the use of ECAs by older adults with cognitive impairment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".