Affective effects of agent proximity in conversational systems

Authors:
Timo Partala;Veikko Surakka;Jussi Lahti
Affiliations:
University of Tampere, Finland;University of Tampere, Finland;University of Tampere, Finland
Venue:
Proceedings of the third Nordic conference on Human-computer interaction
Year:
2004

Citing 3
Cited 6

The media equation: how people treat computers, television, and new media like real people and places

The media equation: how people treat computers, television, and new media like real people and places
Personal space in a virtual community

CHI 98 Cconference Summary on Human Factors in Computing Systems
The impact of animated interface agents: a review of empirical research

International Journal of Human-Computer Studies

Measuring bodily responses to virtual faces with a pressure sensitive chair

Proceedings of the 5th Nordic conference on Human-computer interaction: building bridges
'Do you smell rotten eggs?': evaluating interactions with mobile agents in crisis response situations

Proceedings of the 11th International Conference on Human-Computer Interaction with Mobile Devices and Services
The evaluation of empathy, autonomy and touch to inform the design of an environmental monitoring robot

ICSR'10 Proceedings of the Second international conference on Social robotics
Voluntary facial activations regulate physiological arousal and subjective experiences during virtual social stimulation

ACM Transactions on Applied Perception (TAP)
Let's come together: social navigation behaviors of virtual and real humans

INTETAIN'05 Proceedings of the First international conference on Intelligent Technologies for Interactive Entertainment
A proxemic-based HRI testbed

Proceedings of the Workshop on Performance Metrics for Intelligent Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The aim of this study was to investigate, if the simulated proximity level of an anthropomorphic conversational agent and the affective contents in the agent's speech influence the subjects' affective experiences. Eight subjects were exposed to messages given by the agent using synthetic speech. The agent character's simulated proximity level (intimate, personal, social, and public) and the affective contents of the speech message (negative, neutral, and positive) were systematically varied in the experiment. The proximity levels were simulated by displaying the agent on a screen in different sizes. After each speech message, the subjects rated their affective experience on four scales: valence, arousal, dominance, and message intimacy. They also chose a preferred agent proximity level. The results showed that by manipulating the agent's simulated proximity level, experienced dominance could be significantly influenced. Further, by manipulating the affective contents of the speech, experienced valence and intimacy could be significantly influenced. The personal and social proximity levels were preferred by the subjects.