JMIR Publications

ABSTRACT

Background:

There is an urgent need to innovate in methods of health education, which can often be resource and time intensive. Micro-interventions have shown promise as a platform for rapid, tailored resource dissemination yet have been under-explored as a method of standardized health or dietary education; social media chatbots display unique potential as a modality for accessible, efficient, and affordable educational micro-interventions.

Objective:

This study aims to provide public health professionals practical recommendations on the use of social media chatbots for health education through applied experiences from a novel social media chatbot intervention aimed at improving dietary attitudes and self-efficacy among South Asian young adults.

Methods:

In 2023, the “Roti” chatbot was developed on Facebook and Instagram to administer a 4-lesson tailored dietary health curriculum, informed by formative research and the Theory of Planned Behavior (TPB), to 18–29-year-old South Asian Americans. Each lesson (10-15 mins) consisted of 40-50 pre-scripted interactive texts with the chatbot (including multiple choice and open-response questions). A pre-intervention survey determined which lesson(s) were suggested to participants based on their unique needs, and a post-intervention, TPB-informed survey assessed changes in attitudes, self-efficacy, and user experiences (User Experience Questionnaire, UEQ). Challenges encountered and solutions developed during the chatbot implementation were also documented.

Results:

Data from 168 participants of the intervention (55% Facebook, 45% Instagram) were analyzed (mean age 24.5, 76.8% female). Participants completed an average of 2.6 lessons (13.9 minutes per lesson) and answered an average of 75% of questions asked by the chatbot. Most reported a positive chatbot experience (UEQ 1.34, 69.8% positive), with pragmatic quality being higher than hedonic quality (75.9% vs. 55.2% positive evaluation); younger participants reported greater hedonic quality (p=0.040). On a scale of 10 (highest agreement), participants reported that the chatbot was relevant (8.53), they learned something new (8.24), and helpful (8.28). Qualitative data reveled appreciation for the cheerful, interactive messaging of the chatbot, and outlined areas of improvement for the length, timing, and scope of text content. The use of quick replies, checkpoints, online forums, and self-administered troubleshooting were some solutions developed to meet challenges experienced.

Conclusions:

The implementation of a standardized, tailored health education curriculum through an interactive social media chatbot displayed strong feasibility. Lessons learned from challenges encountered and user input provide a tangible roadmap for future exploration of such chatbots for accessible, engaging health interventions.