Conversational agents in healthcare: a scoping review of their behavior change techniques and underpinning theory (Preprint)

Abstract

Conversational agents (CAs) are increasingly used in healthcare to deliver behavior change interventions. Their evaluation often includes categorizing the behavior change techniques (BCTs), using a classification system of which the BCT Taxonomy V1 is one of the most common. Previous studies have presented descriptive summaries of behavior change interventions delivered by CAs, but no in-depth study reporting the use of BCTs in these interventions has been published to date.

We aimed to describe behavior change interventions delivered by CAs and identify the behavior change techniques (BCTs) and theories guiding their design.

We searched PubMed, Embase, Cochrane’s CENTRAL, and the first ten pages of Google and Google Scholar in April 2021. We included primary, experimental studies evaluating a behavior change intervention delivered by a CA. BCTs coding followed the BCT Taxonomy v1. Two independent reviewers selected the studies and extracted the data. Descriptive analysis and frequent itemset mining to identify BCT clusters were performed.

We included 47 studies reporting on mental health (n=19, 40%), chronic disorders (n=14, 30%), and lifestyle change (n=14, 30%) interventions. There were 20 embodied CAs (43%) and 27 CAs (57%) represented a female character. Most CAs were rule-based (n=34, 72%). Experimental interventions included 63 BCTs, (mean: 9 BCTs, range 2-21), while comparisons included 32 BCTs (mean: 2 BCTs, range 2-17). Most interventions included BCTs 4.1 instructions on how to perform a behavior (n=34, 72%), 3.3 social support (emotional) (n=27, 57%) and 1.2 problem solving (n=24, 51%). A total of 12 studies (26%) were informed by a behavior change theory, mainly the Transtheoretical Model and the Social Cognitive Theory. Studies using the same behavior change theory included different BCTs.

There is a need for the more explicit use of behavior change theories and improved reporting of BCTs in CA interventions to enhance the analysis of intervention effectiveness and improve the reproducibility of research.