Embodied Conversational Agent Appearance for Health Assessment of Older Adults: Explorative Study

Abstract

Background Embodied conversational agents (ECAs) have great potential for health apps but are rarely investigated as part of such apps. To promote the uptake of health apps, we need to understand how the design of ECAs can influence the preferences, motivation, and behavior of users. Objective This is one of the first studies that investigates how the appearance of an ECA implemented within a health app affects users’ likeliness of following agent advice, their perception of agent characteristics, and their feeling of rapport. In addition, we assessed usability and intention to use. Methods The ECA was implemented within a frailty assessment app in which three health questionnaires were translated into agent dialogues. In a within-subject experiment, questionnaire dialogues were randomly offered by a young female agent or an older male agent. Participants were asked to think aloud during interaction. Afterward, they rated the likeliness of following the agent’s advice, agent characteristics, rapport, usability, and intention to use and participated in a semistructured interview. Results A total of 20 older adults (72.2 [SD 3.5] years) participated. The older male agent was perceived as more authoritative than the young female agent (P=.03), but no other differences were found. The app scored high on usability (median 6.1) and intention to use (median 6.0). Participants indicated they did not see an added value of the agent to the health app. Conclusions Agent age and gender little influence users’ impressions after short interaction but remain important at first glance to lower the threshold to interact with the agent. Thus, it is important to take the design of ECAs into account when implementing them into health apps.

Research Trends in Artificial Intelligence Applications in Human Factors Health Care: Mapping Review

“…From a psychological perspective, emotions might facilitate perception [ 76 ]. One study in our review measured users’ perception of an AI-based conversational agent [ 70 ], and another study developed an AI algorithm for real-time detection of patient emotional states and behavior adaptation to encourage positive health care experiences [ 59 ].…”

“…Most patients found the system easy to use and would recommend it to others 523 patients Survey study to measure ease of use To understand the usability, acceptability, and utility of AI-based symptom assessment and advice technology Miller et al [69] The older male conversational agent was perceived as more authoritative than the young female agent (P=.03). Participants did not see an added value of the agent to the health app 20 patients Interview study: Acosta and Ward Scale [71] To analyze the impact of an embodied conversational agent's appearance on user perception ter Stal et al [70] Sixteen children found the chatbot useful and 19 found it easy to use…”

Supporting eating behaviour of community-dwelling older adults: co-design of an embodied conversational agent

“…ECAs have great potential among our target group as well, as earlier studies show high ratings of acceptance, enjoyment and usability of ECAs among older adults Bickmore et al 2013;Ponathil et al 2020;). An example is 'Sylvia', which can be seen in Figure 1 (ter Stal et al 2020). Sylvia is part of a frailty assessment web app, and aims to counter frailty by offering older adults training modules in the domains of healthy nutrition and physical and cognitive training.…”

“… 2020 ; ter Stal et al. 2020 ). An example is ‘Sylvia’, which can be seen in Figure 1 (ter Stal et al.…”

Virtual Agent Representation for Critical Transactions

“…This entails a growing research interest in the various aspects of virtual agent design, with representation aspects playing a significant role. Generally, having a representation is advantageous to virtual agents, and it has been shown to improve social presence [3] and spatial presence [13], the establishment of positive impressions [19], the perception of agent credibility [2], the generation of affective influence [1], and the overall user experience [13]. However, it can also have an adverse impact on user-agent interaction, e.g., in the so-called Uncanny Valley issue [12], or lead to a reduced trustworthiness of virtual agents [7].…”