Let's talk! Socially intelligent agents for language conversation training

H. Prendinger, M. Ishizuka

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

This paper promotes socially intelligent animated agents for the pedagogical task of English conversation training for native speakers of Japanese. Since student-agent conversations are realized as role-playing interactions, strong requirements are imposed on the agents' affective and social abilities. As a novel feature, social role awareness is introduced to animated conversational agents, that are by now strong affective reasoners, but otherwise often lack the social competence observed in humans. In particular, humans may easily adjust their behaviour depending on their respective role in a social setting, whereas their synthetic pendants tend to be driven mostly by emotions and personality. Our main contribution is the incorporation of a "social filter program" to mental models of animated agents. This program may qualify an agent's expression of its emotional state by the social context, thereby enhancing the agent's believability as a conversational partner. Our implemented system is web-based and demonstrates socially aware animated agents in a virtual coffee shop environment. An experiment with our conversation system shows that users consider socially aware agents as more natural than agents that violate conventional practices.

Original languageEnglish
Pages (from-to)465-471
Number of pages7
JournalIEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.
Volume31
Issue number5
DOIs
Publication statusPublished - 2001 Sep
Externally publishedYes

Fingerprint

Coffee
Intelligent agents
Intelligent Agents
Students
Experiments
Training
Language
Mental Models
Violate
Web-based
Tend
Filter

Keywords

  • Affective reasoning
  • Animated agents
  • Believability
  • Emotion expression
  • Social dimension in communication
  • Social role awareness

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Let's talk! Socially intelligent agents for language conversation training. / Prendinger, H.; Ishizuka, M.

In: IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans., Vol. 31, No. 5, 09.2001, p. 465-471.

Research output: Contribution to journalArticle

@article{c2f184241f7641ee9fffd0dde48a5d2f,
title = "Let's talk! Socially intelligent agents for language conversation training",
abstract = "This paper promotes socially intelligent animated agents for the pedagogical task of English conversation training for native speakers of Japanese. Since student-agent conversations are realized as role-playing interactions, strong requirements are imposed on the agents' affective and social abilities. As a novel feature, social role awareness is introduced to animated conversational agents, that are by now strong affective reasoners, but otherwise often lack the social competence observed in humans. In particular, humans may easily adjust their behaviour depending on their respective role in a social setting, whereas their synthetic pendants tend to be driven mostly by emotions and personality. Our main contribution is the incorporation of a {"}social filter program{"} to mental models of animated agents. This program may qualify an agent's expression of its emotional state by the social context, thereby enhancing the agent's believability as a conversational partner. Our implemented system is web-based and demonstrates socially aware animated agents in a virtual coffee shop environment. An experiment with our conversation system shows that users consider socially aware agents as more natural than agents that violate conventional practices.",
keywords = "Affective reasoning, Animated agents, Believability, Emotion expression, Social dimension in communication, Social role awareness",
author = "H. Prendinger and M. Ishizuka",
year = "2001",
month = "9",
doi = "10.1109/3468.952722",
language = "English",
volume = "31",
pages = "465--471",
journal = "IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans",
issn = "1083-4427",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Let's talk! Socially intelligent agents for language conversation training

AU - Prendinger, H.

AU - Ishizuka, M.

PY - 2001/9

Y1 - 2001/9

N2 - This paper promotes socially intelligent animated agents for the pedagogical task of English conversation training for native speakers of Japanese. Since student-agent conversations are realized as role-playing interactions, strong requirements are imposed on the agents' affective and social abilities. As a novel feature, social role awareness is introduced to animated conversational agents, that are by now strong affective reasoners, but otherwise often lack the social competence observed in humans. In particular, humans may easily adjust their behaviour depending on their respective role in a social setting, whereas their synthetic pendants tend to be driven mostly by emotions and personality. Our main contribution is the incorporation of a "social filter program" to mental models of animated agents. This program may qualify an agent's expression of its emotional state by the social context, thereby enhancing the agent's believability as a conversational partner. Our implemented system is web-based and demonstrates socially aware animated agents in a virtual coffee shop environment. An experiment with our conversation system shows that users consider socially aware agents as more natural than agents that violate conventional practices.

AB - This paper promotes socially intelligent animated agents for the pedagogical task of English conversation training for native speakers of Japanese. Since student-agent conversations are realized as role-playing interactions, strong requirements are imposed on the agents' affective and social abilities. As a novel feature, social role awareness is introduced to animated conversational agents, that are by now strong affective reasoners, but otherwise often lack the social competence observed in humans. In particular, humans may easily adjust their behaviour depending on their respective role in a social setting, whereas their synthetic pendants tend to be driven mostly by emotions and personality. Our main contribution is the incorporation of a "social filter program" to mental models of animated agents. This program may qualify an agent's expression of its emotional state by the social context, thereby enhancing the agent's believability as a conversational partner. Our implemented system is web-based and demonstrates socially aware animated agents in a virtual coffee shop environment. An experiment with our conversation system shows that users consider socially aware agents as more natural than agents that violate conventional practices.

KW - Affective reasoning

KW - Animated agents

KW - Believability

KW - Emotion expression

KW - Social dimension in communication

KW - Social role awareness

UR - http://www.scopus.com/inward/record.url?scp=0035439130&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035439130&partnerID=8YFLogxK

U2 - 10.1109/3468.952722

DO - 10.1109/3468.952722

M3 - Article

VL - 31

SP - 465

EP - 471

JO - IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans

JF - IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans

SN - 1083-4427

IS - 5

ER -