Abstract
Background: Embodied conversational agents (ECAs) are increasingly used in healthcare applications (apps) however their acceptability in type 2 diabetes (T2D) self-management apps has not yet been investigated. Objective: To evaluate the acceptability of the ECA (Laura), used to deliver diabetes self-management education and support in the My Diabetes Coach (MDC) app. Methods: A sequential mixed methods design was applied. Adults with T2D allocated to the intervention arm of the MDC trial used the MDC app over a 12- month period. At 6 months, they completed questions assessing their interaction with, and attitudes to, the ECA. In-depth qualitative interviews were conducted with a sub-sample of intervention arm participants to explore their experiences of the ECA. Interview questions included participant perceptions of Laura, including their initial impression of her (and how this changed over time), her personality and ‘human’ character. Quantitative and qualitative data were interpreted through integrated synthesis. Results: Of the 93 intervention participants, 44 (47.3%) were women, mean±SD age was 55±10 years and baseline HbA1c was 7.3±1.5%. Sixty-six (71%) provided survey responses. Of these, most described Laura as being helpful (85%), friendly (85%), competent (84%), trustworthy (72%), and likable (60%). Some described Laura as not real (39%), boring (39%) and annoying (30%). Participants reported that interacting with Laura made them feel more motivated (43%), comfortable (36%), confident (21%), happy (16%) and hopeful (12%). Nineteen percent were frustrated by their interaction with Laura and 16% of participants reported that interacting with Laura made them feel guilty. Four themes emerged from the qualitative data (N=19): 1) Perceived role: a friendly coach rather than a health professional; 2) Perceived support: emotional and motivational; 3) Embodiment preference: a human-like character is acceptable; and 4) Room for improvement: greater congruence needed between Laura’s words and actions. Conclusions: These findings suggest an ECA is an acceptable means to deliver T2D self-management education and support. A human-like character providing ongoing friendly, non-judgemental, emotional and motivational support is well-received. Nevertheless, the ECA can be improved, by increasing congruence between its verbal and non-verbal communication and accommodating user preferences.