MAINTAINING ENGAGEMENT IN LONG-TERM INTERVENTIONS WITH RELATIONAL AGENTS

Authors:
Timothy Bickmore;Daniel Schulman;Langxuan Yin
Affiliations:
Northeastern University, College of Computer and Information Science, Boston, Massachusetts, USA;Northeastern University, College of Computer and Information Science, Boston, Massachusetts, USA;Northeastern University, College of Computer and Information Science, Boston, Massachusetts, USA
Venue:
Applied Artificial Intelligence - Intelligent Virtual Agents
Year:
2010

Citing 0
Cited 7

Is the media equation a flash in the pan?: the durability and longevity of social responses to computers

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Posture, relationship, and discourse structure models of nonverbal behavior for long-term interaction

IVA'11 Proceedings of the 10th international conference on Intelligent virtual agents
Gaze tutor: A gaze-reactive intelligent tutoring system

International Journal of Human-Computer Studies
Requirements and platforms for social agents that alarm and support elderly living alone

ICSR'11 Proceedings of the Third international conference on Social Robotics
Modelling empathy in social robotic companions

UMAP'11 Proceedings of the 19th international conference on Advances in User Modeling
Designing relational agents as long term social companions for older adults

IVA'12 Proceedings of the 12th international conference on Intelligent Virtual Agents
Virtual butlers and real people: styles and practices in long-term use of a companion

Your Virtual Butler

Quantified Score

Hi-index	0.00

Visualization

Abstract

We discuss issues in designing virtual humans for applications that 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.