JMIR Publications

ABSTRACT

Background:

Virtual assistants present unique opportunities to develop innovative health programs that provide appealing, personalised, and convenient health advice and support at low cost and at scale. Design characteristics that influence the look and feel of the virtual assistant, such as visual appearance or language features, may significantly influence users’ psychological and emotional responses and their engagement with the assistant.

Objective:

This scoping review aimed to (1) provide an overview of the experimental research examining how design characteristics of virtual health assistants affect user experience, (2) summarise research findings of experimental research examining how design characteristics of virtual health assistants affect user experience, and (3) if sufficient evidence exists, provide recommendations for the design of virtual health assistants.

Methods:

Five electronic databases (Web of Science, MEDLINE, EMBASE, PsycINFO, and ACM Digital Library) were searched to identify studies that used an experimental design to compare the effects of design characteristics between two or more versions of an interactive virtual health assistant on user experience among adults. Data were synthesised descriptively. Health domains, design characteristics, and outcomes were categorised, and descriptive statistics were used to summarise the body of research. Research findings were categorised as positive, negative or no effect and a matrix of the design characteristics and outcome categories was constructed to summarise the findings.

Results:

After removal of duplicates, 6879 articles were identified from the database searches. Forty-eight articles representing 45 unique studies were included in the review. Most studies used virtual assistants relating to mental health and physical activity, examined conversational style and relational behaviour or visual design, and assessed outcomes in the categories of personality, satisfaction, relationship, and usage intention. Over half of the design characteristics were examined by only one study. Research suggests that empathy and relational behaviour and self-disclosure are related to more positive user experience. Research suggests that having a more realistic human representation for an avatar and having medical attire for the avatar may potentially be related to more positive user experience, but more research is needed.

Conclusions:

There is a burgeoning body of scientific evidence regarding the impact of virtual health assistants’ design characteristics on user experience. Taken together, data suggest that the look and feel of a virtual health assistant does impact user experience, though at present the evidence base is broad and the studies typically small in scale and highly heterogeneous. Virtual health assistants that show empathy, display non-verbal relational behaviours, and that disclose personal information about themselves achieve better user experience. Further research, particularly utilising longitudinal research designs with repeated user interactions, is needed to inform the optimal design of virtual health assistants.