Abstract
Register
Abstract
Year 2021
October 2021

SHBC1674

Abstract Title
Conversational agent for healthy lifestyle behaviour change: an online feasibility study
Authors

D.DHINAGARAN1, S.THIRUNAVUKKARASU2, A.J.SOONG1, Y.L.THENG1, J.D.BEST1, L.TUDOR-CAR1

Institutions

Nanyang Technological University1, McMaster University, Hamilton, Canada2

Background & Hypothesis

The rising incidence of chronic diseases is a growing concern, especially in Singapore with amongst the highest prevalence of diabetes in developed countries. Interventions promoting healthy lifestyle changes have been proven effective in reversing prediabetes. Technologies such as conversational agents could implement such healthy lifestyle changes. This project explored the feasibility and acceptability of using a conversational agent promoting healthy lifestyle changes for the general population in Singapore.

Methods

We performed an online, single-arm feasibility study. Participants were recruited via Facebook and we employed Facebook Messenger to host our conversational agent. The conversations focused on diet, exercise, sleep and stress. Messages were sent four times a week for four weeks. We assessed feasibility of recruitment and retention, participants’ satisfaction and usability of the conversational agent.

Results

Of the eligible participants, 60 provided digital informed consent and completed baseline assessments whilst 56 followed the study through till completion. Retention was high, at 93% (56/60), as was engagement, denoted by 50% of participants communicating with the conversational agent at each interaction. Acceptability, usability, and satisfaction were generally high. Preliminary efficacy needs to be further explored.

Discussion & Conclusion

The delivery of a conversational agent for healthy lifestyle behaviour change via Facebook messenger was feasible and acceptable. We were unable to recruit our planned sample using free options in Facebook exclusively. However, participant retention and conversational agent engagement rates were high. Our findings provide important insights for a future randomised controlled trial.

Top