JMIR Publications

ABSTRACT

Background:

Social care systems worldwide face increasing demographic and financial pressures. This necessitates exploring innovative technological solutions to enhance service delivery without significantly increasing costs. Conversational interfaces, including interactive voice response (IVR), 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 (LLMs) such as ChatGPT has further accelerated interest in conversational 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 synthesise 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: (1) How are conversational systems implemented and used for older adults in a social care context? (2) How are these systems evaluated in terms of usability and effectiveness? (3) What is the impact of conversational AI on social isolation, loneliness, and well-being among older adults?

Methods:

The review will follow the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) and PCC (Population, Concept, Context) 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 onwards. Studies will be included if they empirically examine conversational systems' implementation, evaluation, or impact for older adults (aged 55+) within a social care context. Two independent reviewers will screen articles and extract data. A descriptive analysis will then categorise 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 is expected to begin in March 2025 and be completed and submitted for publication by July 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 synthesising 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.