JMIR Publications

ABSTRACT

Background:

An unhealthy eating pattern and loneliness negatively influence the quality of life in older age. Embodied Conversational Agents (ECAs) are a promising tool to address these health behaviors in an engaging manner.

Objective:

We aim to identify whether ECAs can persuade community-dwelling older adults to dietary behavior change and decrease loneliness, to test these pathways to effects, and to understand use of an ECA. Intervention: The web-based eHealth application PACO is a fully-automated 8-week intervention in which two ECAs engage in dialogue with older adults in order to motivate them towards dietary behavior change and decrease loneliness. PACO was developed via a human-centered and stakeholder-inclusive design approach, and incorporates the Self-Determination Theory and various behavior change techniques.

Methods:

An unblinded randomized controlled trial will be performed. There will be two cohorts, with 30 participants per cohort. Participants in the first cohort will directly receive the PACO application for 8 weeks, while participants in the second cohort receive the PACO application after a waiting list condition of four weeks. Participants will be recruited via social media, an online panel, flyers and advertorials. They are eligible if they are at least 65 years of age, do not have a paid profession, and live independently at home, by themselves. Primary outcomes will be self-assessed via online questionnaires at control, intake, after four and after eight weeks, and include eating behavior and loneliness. In addition, the primary outcome use is measured via data logs. Secondary outcomes will measured at the same four moments, either via self-assessed online questionnaires or an optional interview.

Conclusions:

By unraveling the mechanisms behind the use of a web-based intervention with Embodied Conversational Agents, we hope to be able to gain a fine-grained understanding of both effectiveness and use of ECAs in the health context.