Maintaining Engagement in Long-Term Interventions With Relational Agents

Abstract

We discuss issues in designing virtual humans for applications which require long-term voluntary use, and the problem of maintaining engagement with users over time. Concepts and theories related to engagement from a variety of disciplines are reviewed. We describe a platform for conducting studies into long-term interactions between humans and virtual agents, and present the results of two longitudinal randomized controlled experiments in which the effect of manipulations of agent behavior on user engagement was assessed.

Natural language processing in mental health applications using non-clinical texts

“…Calvo et al life (Bickmore and Gruber 2010;Bickmore, Schulman and Yin 2010). Although short-term engagement is somewhat easier, it is not necessarily a good predictor of health outcomes .…”

You’re Doing It Wrong! Studying Unexpected Behaviors in Child-Robot Interaction

“…The authors found that empathetic robots are more likely to engage users in the long-term and they proposed several guidelines for designing such artificial companions. Other works [1,10] have shown that simpler ways to enhance engagement may as well be effective: [1] describe a series of longitudinal studies on engagement with an agent-like system. They demonstrated that user engagement with an interface agent can be increased using relatively simple techniques and manipulations that make the agent more life-like and human.…”

“…For example [11] define engagement as "the process by which two (or more) participants establish, maintain and end their perceived connections". A definition of long-term engagement is proposed by [1]: "the degree of involvement a user chooses to have with a system over time".…”

Strategic Talk in Film

“…It is accepted that such companions should, as one important functionality, be able to coach and influence their users with regard to health and fitness. Research toward this objective was done by Kidd (2008), Anderson and Anderson (2015), Bickmore, Schulman, and Langxuan (2010), Sloman (2010), von der Puetten, Kraemer, and Eimler (2011), Payr (2013), and many others, most with a focus on the building and maintaining of social relationships as a prerequisite for long-term use, e.g., Cassell and Bickmore (2003). In the field of persuasive technologies in general and agents in particular (e.g., Narita and Kitamura 2010; Pickard 2012), the specific challenges of long-term persuasion have been recognized more recently and begin to be addressed (e.g., in Fritz et al 2014 or Yoshii and Nakajima 2016).…”

“…Studies on long-term relationships with companions, either virtual or embodied as robots, regularly are based on scenarios of health-related counseling, coaching, or monitoring, often with a view to the potential of these technologies for active assisted living for an aging population: physical training (Bickmore, Schulman, and Langxuan 2010), weight loss (Kidd 2008), therapy compliance (Anderson and Anderson 2015), etc. Similar challenges arise for educational robots and agents as soon as they are supposed to motivate and foster substantial long-term learning processes.…”