Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities

Hideyuki Nakanishi, Satoshi Nakazawa, Toru Ishida, Katsuya Takanashi, Katherine Isbister

Research output: Contribution to conferencePaper

25 Citations (Scopus)

Abstract

We sought to create a social embodied conversational agent to support group interactions, using 'balance theory' from social science research on human-human relations. We conducted an experiment to evaluate the social ECA's effectiveness in a group situation, depending upon how strongly it mediated the conversation among group members. First, we confirmed that it could win favorable feelings from subjects by showing an agreeing attitude to them and, conversely, unfavorable feelings by showing a disagreeing attitude. Next, we validated balance theory as a rule governing both agent-human relations and human relations if the social ECA highly mediated the conversation. We found that the social ECA's effectiveness was very low if it did not control turn-taking, and if the human pair had a chance to converse extensively with one another. Conversation analysis corroborated these results.

Original languageEnglish
Pages717-724
Number of pages8
Publication statusPublished - 2003 Dec 1
Externally publishedYes
EventProceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03 - Melbourne, Vic., Australia
Duration: 2003 Jul 142003 Jul 18

Conference

ConferenceProceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03
CountryAustralia
CityMelbourne, Vic.
Period03/7/1403/7/18

Fingerprint

Software agents
Social sciences
Experiments

Keywords

  • Agent-mediated communities
  • Balance theory
  • Embodied conversational agents
  • Social ECAs
  • Virtual communities
  • Virtual environments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Nakanishi, H., Nakazawa, S., Ishida, T., Takanashi, K., & Isbister, K. (2003). Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities. 717-724. Paper presented at Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03, Melbourne, Vic., Australia.

Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities. / Nakanishi, Hideyuki; Nakazawa, Satoshi; Ishida, Toru; Takanashi, Katsuya; Isbister, Katherine.

2003. 717-724 Paper presented at Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03, Melbourne, Vic., Australia.

Research output: Contribution to conferencePaper

Nakanishi, H, Nakazawa, S, Ishida, T, Takanashi, K & Isbister, K 2003, 'Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities', Paper presented at Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03, Melbourne, Vic., Australia, 03/7/14 - 03/7/18 pp. 717-724.
Nakanishi H, Nakazawa S, Ishida T, Takanashi K, Isbister K. Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities. 2003. Paper presented at Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03, Melbourne, Vic., Australia.
Nakanishi, Hideyuki ; Nakazawa, Satoshi ; Ishida, Toru ; Takanashi, Katsuya ; Isbister, Katherine. / Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities. Paper presented at Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03, Melbourne, Vic., Australia.8 p.
@conference{0fbc172e580c4cce84bd9a31485cebe1,
title = "Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities",
abstract = "We sought to create a social embodied conversational agent to support group interactions, using 'balance theory' from social science research on human-human relations. We conducted an experiment to evaluate the social ECA's effectiveness in a group situation, depending upon how strongly it mediated the conversation among group members. First, we confirmed that it could win favorable feelings from subjects by showing an agreeing attitude to them and, conversely, unfavorable feelings by showing a disagreeing attitude. Next, we validated balance theory as a rule governing both agent-human relations and human relations if the social ECA highly mediated the conversation. We found that the social ECA's effectiveness was very low if it did not control turn-taking, and if the human pair had a chance to converse extensively with one another. Conversation analysis corroborated these results.",
keywords = "Agent-mediated communities, Balance theory, Embodied conversational agents, Social ECAs, Virtual communities, Virtual environments",
author = "Hideyuki Nakanishi and Satoshi Nakazawa and Toru Ishida and Katsuya Takanashi and Katherine Isbister",
year = "2003",
month = "12",
day = "1",
language = "English",
pages = "717--724",
note = "Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS 03 ; Conference date: 14-07-2003 Through 18-07-2003",

}

TY - CONF

T1 - Can Software Agents Influence Human Relations? - Balance Theory in Agent-mediated Communities

AU - Nakanishi, Hideyuki

AU - Nakazawa, Satoshi

AU - Ishida, Toru

AU - Takanashi, Katsuya

AU - Isbister, Katherine

PY - 2003/12/1

Y1 - 2003/12/1

N2 - We sought to create a social embodied conversational agent to support group interactions, using 'balance theory' from social science research on human-human relations. We conducted an experiment to evaluate the social ECA's effectiveness in a group situation, depending upon how strongly it mediated the conversation among group members. First, we confirmed that it could win favorable feelings from subjects by showing an agreeing attitude to them and, conversely, unfavorable feelings by showing a disagreeing attitude. Next, we validated balance theory as a rule governing both agent-human relations and human relations if the social ECA highly mediated the conversation. We found that the social ECA's effectiveness was very low if it did not control turn-taking, and if the human pair had a chance to converse extensively with one another. Conversation analysis corroborated these results.

AB - We sought to create a social embodied conversational agent to support group interactions, using 'balance theory' from social science research on human-human relations. We conducted an experiment to evaluate the social ECA's effectiveness in a group situation, depending upon how strongly it mediated the conversation among group members. First, we confirmed that it could win favorable feelings from subjects by showing an agreeing attitude to them and, conversely, unfavorable feelings by showing a disagreeing attitude. Next, we validated balance theory as a rule governing both agent-human relations and human relations if the social ECA highly mediated the conversation. We found that the social ECA's effectiveness was very low if it did not control turn-taking, and if the human pair had a chance to converse extensively with one another. Conversation analysis corroborated these results.

KW - Agent-mediated communities

KW - Balance theory

KW - Embodied conversational agents

KW - Social ECAs

KW - Virtual communities

KW - Virtual environments

UR - http://www.scopus.com/inward/record.url?scp=1142304658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1142304658&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:1142304658

SP - 717

EP - 724

ER -