P4‐148: ECHOES AROUND THE HOME: CAN THE AMAZON ECHO BE USED IN THE HOME TO HELP THOSE LIVING WITH DEMENTIA?
Bibliographic record
Abstract
People living with dementia face many challenges to their independence as the condition progresses, often increasingly relying on their caregivers for tasks which had previously been simpler. Voice-assistive technologies represent a way to enable independence. In this work we investigate the effect of the Amazon Echo on people with Posterior Cortical Atrophy (PCA), most commonly an atypical variant of Alzheimer's Disease that primarily affects visual processing. Six people with PCA along with their family caregiver were recruited. Each household was given three Amazon Echo Dot devices, smart lights, a subscription to Spotify and access to audiobooks. Before receiving the devices, people with dementia and caregivers took part in separate semi structured interviews, which were structured around technology and independence. Households were given the devices for ten weeks, and then a follow up interview was carried out and all ‘Alexa interactions’ (Figure 2) were mined from Amazon using the ESCAPE protocol [1]. We observed from qualitative interview data that the Amazon Echo was generally well received and that it facilitated independence for participants. Contrary to our initial hypothesis, independence was in the majority facilitated by the entertainment functionality more than the practical task-related features of the device. Using the Echo devices as a method of data collection proved to be highly successful, with an average of over 3000 recordings per household (Figure 1). These data support findings from the qualitative interviews about how the devices were used (Figure 2). These data also highlight groupwise differences between the PCA and control groups, for example the PCA group was significantly more likely to repeat the wake word when using the devices (p< 0.034, U=24877238). For this group of people with PCA the Amazon Echo facilitated independence overall. The Echo is also a useful device for collecting large, rich datasets from people with dementia in a naturalistic setting. We hope that findings from this proof of concept trial can inform further research into voice-assistive technologies for people with dementia. Reference: Firth et al, arXiv:1706.06176 [cs.HC.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 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".