A Framework for Design of Conversational Agents to Support Health Self-Care for Older Adults

Abstract

Objective We examined the potential of conversational agents (CAs) to support older adults’ self-care related to chronic illness in light of lessons learned from decades of pedagogical agent research, which investigates the impact and efficacy of CAs for a wide range of learners. Background The role of CAs in education (i.e., pedagogical agents) has been long studied, but their potential for supporting self-care has received less attention, especially for older adults. Methods We reviewed work on pedagogical agents and considered how it informs the design of CAs for older adults. We propose a framework for designing CAs to support older adult self-care, which organizes a review of work in this area and integration with the pedagogical agent literature. Results Our review of the pedagogical agent literature revealed an evolution from teaching machines to interactive, social systems that influence student motivational as well as learning outcomes. To integrate this review with work on CAs and self-care, we developed a framework that specifies how self-care goals evolve with stages of an illness, communication goals that support self-care at each stage, patient needs, and requirements for CAs to support these needs. The review identified an agenda for future research on CA functions and features that help older adults accept need for self-care, establish self-care, and sustain self-care over time. Conclusions Integrating insights from the pedagogical agent literature with research on developing CAs for self-care defines an agenda for developing and evaluating CAs to help older adults manage illness.

Supporting mental health self-care discovery through a chatbot

“…There is evidence that the personality of the user makes a difference in how trust between the user and the chatbot is formed ( 19 , 37 ). In line with our findings, previous studies have frequently mentioned human likeness as a key aspect of trust ( 9 , 38 ). Indeed, in our study, six participants directly mentioned how the chatbot and its human-likeness positively affected their trust in the system.…”

“…Chatbot behaviour and human likeness are essential factors in forming trust in chatbots ( 9 , 20 , 38 ). There is evidence that the personality of the user makes a difference in how trust between the user and the chatbot is formed ( 19 , 37 ).…”

“…A community sharing a similar burden can be an excellent resource for self-care methods. While various other means of serving these methods exist, researchers are currently actively looking into the affordances of chat-based conversational agents, chatbots, due to their inherent relatability and rapidly increasing interaction capabilities (see, e.g., ( 9 , 10 )).…”

“…While chatbots are not suitable to provide the users with actual clinical intervention, they are an excellent way to provide mental health counselling, such as presenting the users with various self-care methods to help them improve their mental health ( 18 ). While most research for chatbots offering self-care focuses on young people, it has been shown to be effective for older adults, as well, as is shown by Morrow et al, who present a framework for the design of chatbots on health-related self-care for older adults ( 9 ). As is found in the review by Abd-Alrazaq et.…”

Division 21 has been devoted to human-centered design since the 1950s: Comment on Lyon, Brewer, and Areán (2020).

“…It has tracks in clinical and consumer health care information technology, education and simulation, hospital environments, medical and drug delivery devices, and patient safety research and initiatives. An example article, coauthored by Division 21 past-presidents, Dan Morrow and Wendy Rogers, focuses on developing and evaluating conversational agents to assist older adults in managing illnesses (Morrow et al, 2020).…”