Four-participant group conversation

A facilitation robot controlling engagement density as the fourth participant

Yoichi Matsuyama, Iwao Akiba, Shinya Fujie, Tetsunori Kobayashi

研究成果: Article

10 引用 (Scopus)

抄録

In this paper, we present a framework for facilitation robots that regulate imbalanced engagement density in a four-participant conversation as the forth participant with proper procedures for obtaining initiatives. Four is the special number in multiparty conversations. In three-participant conversations, the minimum unit for multiparty conversations, social imbalance, in which a participant is left behind in the current conversation, sometimes occurs. In such scenarios, a conversational robot has the potential to objectively observe and control situations as the fourth participant. Consequently, we present model procedures for obtaining conversational initiatives in incremental steps to harmonize such four-participant conversations. During the procedures, a facilitator must be aware of both the presence of dominant participants leading the current conversation and the status of any participant that is left behind. We model and optimize these situations and procedures as a partially observable Markov decision process (POMDP), which is suitable for real-world sequential decision processes. The results of experiments conducted to evaluate the proposed procedures show evidence of their acceptability and feeling of groupness.

元の言語English
ページ(範囲)1-24
ページ数24
ジャーナルComputer Speech and Language
33
発行部数1
DOI
出版物ステータスPublished - 2015

Fingerprint

Robot
Robots
Partially Observable Markov Decision Process
Experiments
Optimise
Engagement
Scenarios
Unit
Evaluate
Model
Experiment

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Theoretical Computer Science

これを引用

@article{e17f126090b44fcaaec884e7ed2a38b7,
title = "Four-participant group conversation: A facilitation robot controlling engagement density as the fourth participant",
abstract = "In this paper, we present a framework for facilitation robots that regulate imbalanced engagement density in a four-participant conversation as the forth participant with proper procedures for obtaining initiatives. Four is the special number in multiparty conversations. In three-participant conversations, the minimum unit for multiparty conversations, social imbalance, in which a participant is left behind in the current conversation, sometimes occurs. In such scenarios, a conversational robot has the potential to objectively observe and control situations as the fourth participant. Consequently, we present model procedures for obtaining conversational initiatives in incremental steps to harmonize such four-participant conversations. During the procedures, a facilitator must be aware of both the presence of dominant participants leading the current conversation and the status of any participant that is left behind. We model and optimize these situations and procedures as a partially observable Markov decision process (POMDP), which is suitable for real-world sequential decision processes. The results of experiments conducted to evaluate the proposed procedures show evidence of their acceptability and feeling of groupness.",
keywords = "Conversational strategy, Engagement density control, Facilitation robot, Markov decision process, Multimodal processing, Multiparty conversation, Partially observable",
author = "Yoichi Matsuyama and Iwao Akiba and Shinya Fujie and Tetsunori Kobayashi",
year = "2015",
doi = "10.1016/j.csl.2014.12.001",
language = "English",
volume = "33",
pages = "1--24",
journal = "Computer Speech and Language",
issn = "0885-2308",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Four-participant group conversation

T2 - A facilitation robot controlling engagement density as the fourth participant

AU - Matsuyama, Yoichi

AU - Akiba, Iwao

AU - Fujie, Shinya

AU - Kobayashi, Tetsunori

PY - 2015

Y1 - 2015

N2 - In this paper, we present a framework for facilitation robots that regulate imbalanced engagement density in a four-participant conversation as the forth participant with proper procedures for obtaining initiatives. Four is the special number in multiparty conversations. In three-participant conversations, the minimum unit for multiparty conversations, social imbalance, in which a participant is left behind in the current conversation, sometimes occurs. In such scenarios, a conversational robot has the potential to objectively observe and control situations as the fourth participant. Consequently, we present model procedures for obtaining conversational initiatives in incremental steps to harmonize such four-participant conversations. During the procedures, a facilitator must be aware of both the presence of dominant participants leading the current conversation and the status of any participant that is left behind. We model and optimize these situations and procedures as a partially observable Markov decision process (POMDP), which is suitable for real-world sequential decision processes. The results of experiments conducted to evaluate the proposed procedures show evidence of their acceptability and feeling of groupness.

AB - In this paper, we present a framework for facilitation robots that regulate imbalanced engagement density in a four-participant conversation as the forth participant with proper procedures for obtaining initiatives. Four is the special number in multiparty conversations. In three-participant conversations, the minimum unit for multiparty conversations, social imbalance, in which a participant is left behind in the current conversation, sometimes occurs. In such scenarios, a conversational robot has the potential to objectively observe and control situations as the fourth participant. Consequently, we present model procedures for obtaining conversational initiatives in incremental steps to harmonize such four-participant conversations. During the procedures, a facilitator must be aware of both the presence of dominant participants leading the current conversation and the status of any participant that is left behind. We model and optimize these situations and procedures as a partially observable Markov decision process (POMDP), which is suitable for real-world sequential decision processes. The results of experiments conducted to evaluate the proposed procedures show evidence of their acceptability and feeling of groupness.

KW - Conversational strategy

KW - Engagement density control

KW - Facilitation robot

KW - Markov decision process

KW - Multimodal processing

KW - Multiparty conversation

KW - Partially observable

UR - http://www.scopus.com/inward/record.url?scp=84921636496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84921636496&partnerID=8YFLogxK

U2 - 10.1016/j.csl.2014.12.001

DO - 10.1016/j.csl.2014.12.001

M3 - Article

VL - 33

SP - 1

EP - 24

JO - Computer Speech and Language

JF - Computer Speech and Language

SN - 0885-2308

IS - 1

ER -