Establishing and maintaining long-term human-computer relationships

Abstract

This research investigates the meaning of "human-computer relationship" and presents techniques for constructing, maintaining, and evaluating such relationships, based on research in social psychology, sociolinguistics, communication and other social sciences. Contexts in which relationships are particularly important are described, together with specific benefits (like trust) and task outcomes (like improved learning) known to be associated with relationship quality. We especially consider the problem of designing for long-term interaction, and define relational agents as computational artifacts designed to establish and maintain long-term social-emotional relationships with their users. We construct the first such agent, and evaluate it in a controlled experiment with 101 users who were asked to interact daily with an exercise adoption system for a month. Compared to an equivalent task-oriented agent without any deliberate social-emotional or relationship-building skills, the relational agent was respected more, liked more, and trusted more, even after four weeks of interaction. Additionally, users expressed a significantly greater desire to continue working with the relational agent after the termination of the study. We conclude by discussing future directions for this research together with ethical and other ramifications of this work for HCI designers.

Promoting motivation with virtual agents and avatars: role of visual presence and appearance

“…Interestingly, while an agent with greater computational functionality may be perceived as more believable, research indicates that learners perceive, interact socially with and are influenced by anthropomorphic agents even when their functionality and adaptability are limited (e.g. Baylor 2005;Baylor & Plant 2005;Baylor & Kim 2005aRyu & Baylor 2005;Kim & Baylor 2006, 2007bGuadagno et al 2007;Kim et al 2007;Rosenberg-Kima et al 2007. Consequently, designing agents as social models is within the reach of many educators, health promoters and others who wish to promote new attitudes, change behaviours or positively influence others.…”

Using Socially Assistive Human–Robot Interaction to Motivate Physical Exercise for Older Adults1

“…Bickmore and Picard developed a computer-based virtual relational agent that served as a daily exercise advisor by engaging the user in conversation and providing educational information about walking for exercise, asking about the user's daily activity levels, tracking user progress over time while giving feedback, and engaging the user in relational dialog [33]. Kidd and Breazeal developed a tabletop robot to serve as a daily weight-loss advisor, which interacted through a touchscreen interface, tracked user progress and the user-robot relationship state over time, and was tested in a six-week field study with participants at home [51].…”

“…Many social intricacies contribute to the foundation of a meaningful relationship, both in HCI (as detailed by Bickmore and Picard [33]) and in HRI. These include empathy, humor, references to mutual knowledge, continuity behaviors, politeness, and trust, among others.…”

Empathy and Its Modulation in a Virtual Human

“…For instance, it has been shown that empathic virtual humans can reduce stress levels during job interview tasks [17] and that empathic agents are perceived as more likable, trustworthy, and caring [7]. Furthermore, it has been found that empathic virtual humans can evoke empathy in children and can thus teach them to deal with bullying situations [16] and that a virtual human's empathic behavior also contributes to its ability to build and sustain long-term socio-emotional relationships with human partners [3]. However, it has been shown that in a competitive card game scenario, empathic emotions can increase arousal and induce stress in an interaction partner [1].…”