When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation

I.A. de Kok; Dirk K.J. Heylen

doi:10.1007/978-3-642-24600-5_51

When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation

I.A. de Kok, Dirk K.J. Heylen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

4 Citations (Scopus)

3 Downloads (Pure)

Abstract

In this paper we will look into reactive models for embodied conversational agents for generating smiling behavior. One trigger for smiling behaviour is smiling of the human interlocutor which is used in reactive models based on mimicry. However, other features might be useful as well. In order to develop such models we look at the nonverbal context of smiles in human-human conversation. We make a distinction between three types of smiles - amused, polite and embarrassed - and highlighted dierences in context where each type occurs in conversation. Using machine learning techniques we have build predictive models using the nonverbal contextual features analyzed. Results show that reactive models can oer an interesting contribution to the generation of smiling behaviors.

Original language	Undefined
Title of host publication	Proceedings of the 4th 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011
Place of Publication	Berlin
Publisher	Springer
Pages	477-486
Number of pages	10
ISBN (Print)	978-3-642-24599-2
DOIs	https://doi.org/10.1007/978-3-642-24600-5_51
Publication status	Published - Oct 2011
Event	4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011 - Memphis, United States Duration: 9 Oct 2011 → 12 Oct 2011 Conference number: 4

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	6974
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011
Abbreviated title	ASCII
Country/Territory	United States
City	Memphis
Period	9/10/11 → 12/10/11

Keywords

METIS-281604
Machine Learning
IR-78729
EWI-20908
Social Signals
Smiles
HMI-IA: Intelligent Agents
Conversation

Access to Document

10.1007/978-3-642-24600-5_51

http://eprints.eemcs.utwente.nl/secure2/20908/01/acii2011-camera-ready.pdf

Cite this

de Kok, I. A., & Heylen, D. K. J. (2011). When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation. In Proceedings of the 4th 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011 (pp. 477-486). (Lecture Notes in Computer Science; Vol. 6974). Springer. https://doi.org/10.1007/978-3-642-24600-5_51

@inproceedings{5c70289f341548ef93a8da1623284e0a,

title = "When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation",

abstract = "In this paper we will look into reactive models for embodied conversational agents for generating smiling behavior. One trigger for smiling behaviour is smiling of the human interlocutor which is used in reactive models based on mimicry. However, other features might be useful as well. In order to develop such models we look at the nonverbal context of smiles in human-human conversation. We make a distinction between three types of smiles - amused, polite and embarrassed - and highlighted dierences in context where each type occurs in conversation. Using machine learning techniques we have build predictive models using the nonverbal contextual features analyzed. Results show that reactive models can oer an interesting contribution to the generation of smiling behaviors.",

keywords = "METIS-281604, Machine Learning, IR-78729, EWI-20908, Social Signals, Smiles, HMI-IA: Intelligent Agents, Conversation",

author = "{de Kok}, I.A. and Heylen, {Dirk K.J.}",

note = "10.1007/978-3-642-24600-5_51 ; 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011 ; Conference date: 09-10-2011 Through 12-10-2011",

year = "2011",

month = oct,

doi = "10.1007/978-3-642-24600-5_51",

language = "Undefined",

isbn = "978-3-642-24599-2",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "477--486",

booktitle = "Proceedings of the 4th 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011",

address = "Germany",

}

de Kok, IA & Heylen, DKJ 2011, When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation. in Proceedings of the 4th 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011. Lecture Notes in Computer Science, vol. 6974, Springer, Berlin, pp. 477-486, 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011, Memphis, Tennessee, United States, 9/10/11. https://doi.org/10.1007/978-3-642-24600-5_51

When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation. / de Kok, I.A.; Heylen, Dirk K.J.
Proceedings of the 4th 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011. Berlin: Springer, 2011. p. 477-486 (Lecture Notes in Computer Science; Vol. 6974).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - When Do We Smile? Analysis and Modeling of the Nonverbal Context of Listener Smiles in Conversation

AU - de Kok, I.A.

AU - Heylen, Dirk K.J.

N1 - Conference code: 4

PY - 2011/10

Y1 - 2011/10

N2 - In this paper we will look into reactive models for embodied conversational agents for generating smiling behavior. One trigger for smiling behaviour is smiling of the human interlocutor which is used in reactive models based on mimicry. However, other features might be useful as well. In order to develop such models we look at the nonverbal context of smiles in human-human conversation. We make a distinction between three types of smiles - amused, polite and embarrassed - and highlighted dierences in context where each type occurs in conversation. Using machine learning techniques we have build predictive models using the nonverbal contextual features analyzed. Results show that reactive models can oer an interesting contribution to the generation of smiling behaviors.

AB - In this paper we will look into reactive models for embodied conversational agents for generating smiling behavior. One trigger for smiling behaviour is smiling of the human interlocutor which is used in reactive models based on mimicry. However, other features might be useful as well. In order to develop such models we look at the nonverbal context of smiles in human-human conversation. We make a distinction between three types of smiles - amused, polite and embarrassed - and highlighted dierences in context where each type occurs in conversation. Using machine learning techniques we have build predictive models using the nonverbal contextual features analyzed. Results show that reactive models can oer an interesting contribution to the generation of smiling behaviors.

KW - METIS-281604

KW - Machine Learning

KW - IR-78729

KW - EWI-20908

KW - Social Signals

KW - Smiles

KW - HMI-IA: Intelligent Agents

KW - Conversation

U2 - 10.1007/978-3-642-24600-5_51

DO - 10.1007/978-3-642-24600-5_51

M3 - Conference contribution

SN - 978-3-642-24599-2

T3 - Lecture Notes in Computer Science

SP - 477

EP - 486

BT - Proceedings of the 4th 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011

PB - Springer

CY - Berlin

T2 - 4th International Conference on Affective Computing and Intelligent Interaction, ASCII 2011

Y2 - 9 October 2011 through 12 October 2011

ER -