Conversational Systems for Social Care in Older Adults: Protocol for a Scoping Review
Bibliographic record
Abstract
BACKGROUND: Social care systems worldwide face increasing demographic and financial pressures. This necessitates exploring innovative technological solutions to enhance service delivery without substantially increasing costs. Conversational interfaces, including interactive voice response, chatbots, and voice assistants, have gained traction as a means to improve accessibility and efficiency in social care. The rapid development of large language models such as ChatGPT has further accelerated interest in conversational artificial intelligence (AI). These technologies can offer intuitive interactions, particularly for individuals with limited digital literacy. However, their real-world impact, usability, and ethical considerations in social care remain underexplored. OBJECTIVE: This scoping review aims to synthesize existing literature on the implementation, evaluation, and impact of conversational AI systems within social care settings for older adults. The review will identify best practices, current gaps, and future directions for research and implementation. Key research questions include the following: how are conversational systems implemented on a technical level, and how do older adults and their support systems use them in a social care context? What methods are used to evaluate acceptability, usability, and the impact of broad well-being in the context of older adults' social care? and What are conversational technologies' acceptability, usability, and well-being impact in the context of older adults' social care? METHODS: The review will follow the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) and Population, Concept, and Context (PCC) frameworks. A systematic search will be conducted across five databases (IEEE, Web of Science, PubMed, ACM, and Scopus) for English-language articles published from 2019 onward. Studies will be included if they empirically examine conversational systems' implementation, evaluation, or impact for older adults (aged ≥55 years) within a social care context. Two independent reviewers will screen articles and extract data. A descriptive analysis will then categorize findings across key domains such as accessibility, usability, ethical considerations, and well-being outcomes. RESULTS: The results will be included in the scoping review, which began in March 2025. The analysis is underway and is expected to be completed and submitted for publication by September 2025. CONCLUSIONS: This scoping review will provide an overview of the role of conversational AI in social care, highlighting both opportunities and challenges in implementation. By synthesizing existing research, the review will inform future developments in the use of conversational agents to improve social inclusion, engagement, and well-being among older adults. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/72310.
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 | 0.077 | 0.091 |
| Meta-epidemiology (narrow) | 0.005 | 0.005 |
| Meta-epidemiology (broad) | 0.014 | 0.016 |
| Bibliometrics | 0.017 | 0.014 |
| Science and technology studies | 0.005 | 0.005 |
| Scholarly communication | 0.008 | 0.008 |
| Open science | 0.005 | 0.007 |
| Research integrity | 0.008 | 0.008 |
| Insufficient payload (model declined to judge) | 0.080 | 0.012 |
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".