Use and Effect of Web-Based Embodied Conversational Agents for Improving Eating Behavior and Decreasing Loneliness Among Community-Dwelling Older Adults: Protocol for a Randomized Controlled Trial

摘要

Background An unhealthy eating pattern and loneliness negatively influence quality of life in older age. Embodied conversational agents (ECAs) are a promising way to address these health behaviors in an engaging manner. Objective We aim to (1) identify whether ECAs can persuade community-dwelling older adults to change their dietary behavior and whether ECA use can decrease loneliness, (2) test these pathways to effects, and (3) understand the use of an ECA. Methods The web-based eHealth app PACO is a fully automated 8-week intervention in which 2 ECAs engage older adults in dialogue to motivate them to change their dietary behavior and decrease their loneliness. PACO was developed via a human-centered and stakeholder-inclusive design approach and incorporates Self-determination Theory and various behavior change techniques. For this study, an unblinded randomized controlled trial will be performed. There will be 2 cohorts, with 30 participants per cohort. Participants in the first cohort will immediately receive the PACO app for 8 weeks, while participants in the second cohort receive the PACO app after a waiting-list condition of 4 weeks. Participants will be recruited via social media, an online panel, flyers, and advertorials. To be eligible, participants must be at least 65 years of age, must not be in paid employment, and must live alone independently at home. Primary outcomes will be self-assessed via online questionnaires at intake, control, after 4 weeks, and after 8 weeks, and will include eating behavior and loneliness. In addition, the primary outcome—use—will be measured via data logs. Secondary outcomes will be measured at the same junctures, via either validated, self-assessed, online questionnaires or an optional interview. Results As of July 2020, we have begun recruiting participants. Conclusions By unraveling the mechanisms behind the use of a web-based intervention with ECAs, we hope to gain a fine-grained understanding of both the effectiveness and the use of ECAs in the health context.