Umeå University's logo

This article presents an empirical requirement elicitation study for an argumentation-based digital companion for supporting behavior change, whose ultimate goal is the promotion and facilitation of healthy behavior. The study was conducted with non-expert users as well as with health experts and was in part supported by the development of prototypes. It focuses on human-centric aspects, in particular user motivations, as well as on expectations and perceptions regarding the role and interaction behavior of a digital companion. Based on the results of the study, a framework for person tailoring the agent's roles and behaviors, and argumentation schemes are proposed. The results indicate that the extent to which a digital companion argumentatively challenges or supports a user's attitudes and chosen behavior and how assertive and provocative the companion is may have a substantial and individualized effect on user acceptance, as well as on the effects of interacting with the digital companion. More broadly, the results shed some initial light on the perception of users and domain experts of “soft,” meta-level aspects of argumentative dialogue, indicating potential for future research.

Setting goals is a basic functionality of digital behaviour change interventions aimed at improving health. A challenge is to motivate and define personally relevant, small, easy-to-achieve ("baby step") goals, to which a person can adhere to over time. The aim of this work is to contextualize goal setting, to identify potentially conflicting motives that affect goal setting and adherence to goals. The purpose of this study is to investigate how representations of different levels of activity in terms of activity theory, and their values and motives, can be used for goal setting. The study was conducted as a part of the design and development of a digital coach for preventing cardio-vascular diseases and exhaustion syndromes. The content of an early prototype was evaluated with 40 provisional users. This was done through a questionnaire, containing a part of the data collection module of the prototype. The results include a set of activities defined at different levels of activity in terms of activity theory, their potentially conflicting motives and arguments, importance, social and personal value. The results are integrated in an ontology of activity and embedded in a prototype for supporting behaviour change.

The aim of the work presented in this article was to develop a conceptual model for behavior change progress, which could be used for automated assessment of reasons for progress or non-progress. The model was developed based on theories for behavior change, and evaluated by domain experts. The information models of two prototype systems of a digital coach under development for preventing cardio-vascular diseases and stress respectively, were evaluated by comparing the content of the prototypes with concepts in the model. The conceptual model was found useful as instrument to evaluate to what extent the prototypes are based in theories for behavior change, whether some vital information is missing, and to identify mechanisms for short and long time goal setting. Moreover, the connection between the ontology underpinning the prototypes and the conceptual model could be defined. Future work includes the integration of the conceptual model to function as a meta-ontology, which could be used for capturing causal relationships between information collected by the applications at baseline and at runtime.