Tailoring coaching strategies to users’ motivation in a multi-agent health coaching application

Beinema, Tessa; Akker, Harm op den; Velsen, Lex van; Hermens, Hermie

doi:10.1016/j.chb.2021.106787

Cited by 21 publications

(22 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Related literature on MI-techniques applied in both computerized and non-computerized setups [26,37,59] have found MI effective in bringing change to habits, especially through MI treatment integrity code (MITI) [46], stages and techniques of MI [37], Manual for MI Skill Code (MISC) [47], Drinker's Check-Up (DCU) [49]. Recent work with MI-based virtual agents [5,54] use limited response options for users by providing menu-based text-only options. Since MI requires deeper elicitation from the individual needing the assistance, because of the limitation in current agent capabilities in continuing open-ended conversation the automated MI interventions is challenging [45].…”

Section: Agent With Motivational Interviewingmentioning

confidence: 99%

“…In this preliminary stage, following the computerized MI-based Drinker's Check-Up (DCU) [49], our design includes limited response options for users by providing menu-based text-only options. Such limited-option based user response style has been also adopted in recent work with MI-based virtual agents [5,54]. Chatbot Agent Selection: Recent research has started exploring MI-based virtual agents (e.g., chatbot, embodied agent, social robots) [5,54,55] for evoking habit changes.…”

Section: Agent Designmentioning

confidence: 99%

“…Such limited-option based user response style has been also adopted in recent work with MI-based virtual agents [5,54]. Chatbot Agent Selection: Recent research has started exploring MI-based virtual agents (e.g., chatbot, embodied agent, social robots) [5,54,55] for evoking habit changes. However, in those setups, user interaction is still processed mostly as text-based input, if not through Wizard-of-Oz.…”

Section: Agent Designmentioning

confidence: 99%

See 2 more Smart Citations

Mia

Samrose

Hoque

2022

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

Since online discussion platforms can limit the perception of social cues, effective collaboration over videochat requires additional attention to conversational skills. However, self-affirmation and defensive bias theories indicate that feedback may appear confrontational, especially when users are not motivated to incorporate them. We develop a feedback chatbot that employs Motivational Interviewing (MI), a directive counseling method that encourages commitment to behavior change, with the end goal of improving the user's conversational skills. We conduct a within-subject study with 21 participants in 8 teams to evaluate our MI-agent 'MIA' and a non-MI-agent 'Roboto'. After interacting with an agent, participants are tasked with conversing over videochat to evaluate candidate résumés for a job circular. Our quantitative evaluation shows that the MI-agent effectively motivates users, improves their conversational skills, and is likable. Through a qualitative lens, we present the strategies and the cautions needed to fulfill individual and team goals during group discussions. Our findings reveal the potential of the MI technique to improve collaboration and provide examples of conversational tactics important for optimal discussion outcomes.

show abstract

Section: Agent With Motivational Interviewingmentioning

confidence: 99%

Section: Agent Designmentioning

confidence: 99%

Section: Agent Designmentioning

confidence: 99%

See 1 more Smart Citation

Mia

Samrose

Hoque

2022

Proc. ACM Hum.-Comput. Interact.

View full text Add to dashboard Cite

show abstract

“…Topics in the tree may be more or less relevant during the interaction, based on available information such as users' current status (e.g., from sensor data), interaction history (e.g., previously addressed topics and conversation outcomes), and preferred coaching strategy (e.g. from the set of strategies in [2]). Examples of rules to compute the relevance of a topic are conversational (e.g., 'start with an introduction') or task related (e.g., 'discuss goal-setting' when no goal has been set yet or 'increase relevance for inform topics' when the strategy of the agent is health education).…”

Section: The Topic Selection Enginementioning

confidence: 99%

“…Each agent in this council had their own personality, backstory, and expertise (e.g., physical activity or nutrition). Throughout this paper, we will provide examples in the context of this health coaching use case to illustrate the discussed concepts and technical explanations 2 . The application was built on a number of state-of-the-art components from the field of intelligent virtual humans and dialog systems and turned into a versatile, reusable and standalone platform.…”

Section: Introductionmentioning

confidence: 99%

Agents United

Beinema

Davison

Reidsma

et al. 2021

Proceedings of the 21th ACM International Conference on Intelligent Virtual Agents

Self Cite

View full text Add to dashboard Cite

show abstract

Collaboratively Setting Daily Step Goals with a Virtual Coach: Using Reinforcement Learning to Personalize Initial Proposals

Dierikx,

Albers,

Scheltinga

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Goal-setting is commonly used in behavior change applications for physical activity. However, for goals to be effective, they need to be tailored to a user’s situation (e.g., motivation, progress). One way to obtain such goals is a collaborative process in which a healthcare professional and client set a goal together, thus making use of the professional’s expertise and the client’s knowledge about their own situation. As healthcare professionals are not always available, we created a dialog with the virtual coach Steph to collaboratively set daily step goals. Since judgments in human decision-making processes are adjusted based on the starting point or anchor, the first step goal proposal Steph makes is likely to influence the user’s final goal and self-efficacy. Situational factors impacting physical activity (e.g., motivation, self-efficacy, available time) or how users process information (e.g., mood) may determine which initial proposals are most effective in getting users to reach their underlying previous activity-based recommended step goals. Using data from 117 people interacting with Steph for up to five days, we designed a reinforcement learning algorithm that considers users’ current and future situations when choosing an initial step goal proposal. Our simulations show that initial step goal proposals matter: choosing optimal ones based on this algorithm could make it more likely that people move to a situation with high motivation, high self-efficacy, and a favorable daily context. Then, they are more likely to achieve, but also to overachieve, their underlying recommended step goals. Our dataset is publicly available.

show abstract

Tailoring coaching strategies to users’ motivation in a multi-agent health coaching application

Cited by 21 publications

References 64 publications

Mia

Mia

Agents United

Collaboratively Setting Daily Step Goals with a Virtual Coach: Using Reinforcement Learning to Personalize Initial Proposals

Contact Info

Product

Resources

About