Adapting a virtual agent to user personality

Onno Kampman; Farhad Bin Siddique; Yang Yang; Pascale Fung

doi:10.1007/978-3-319-92108-2_13

Adapting a virtual agent to user personality

Onno Kampman, Farhad Bin Siddique^*, Yang Yang, Pascale Fung

^*Corresponding author for this work

Department of Electronic and Computer Engineering

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

10 Citations (Scopus)

Abstract

We propose to adapt a virtual agent called ‘Zara the Supergirl’ to user personality. User personality is deducted through two models, one based on raw audio and the other based on speech transcription text. Both models show good performance, with an average F-score of 69.6 for personality perception from audio, and an average F-score of 71.0 for recognition from text. Both models deploy a Convolutional Neural Network. Through a Human-Agent Interaction study we find correlations between user personality and preferred agent personality. The study suggests that especially the Openness user personality trait correlates with a stronger preference for agents with more gentle personality. People also sense more empathy and enjoy better conversations when agents adapt their personalities.

Original language	English
Title of host publication	Advanced Social Interaction with Agents - 8th International Workshop on Spoken Dialog Systems
Editors	Laurence Devillers, Maxine Eskenazi, Joseph Mariani
Publisher	Springer Verlag
Pages	111-118
Number of pages	8
ISBN (Print)	9783319921075
DOIs	https://doi.org/10.1007/978-3-319-92108-2_13
Publication status	Published - 2019
Event	8th International Workshop on Spoken Dialogue Systems, IWSDS 2017 - Farmington, United States Duration: 6 Jun 2017 → 9 Jun 2017

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	510
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	8th International Workshop on Spoken Dialogue Systems, IWSDS 2017
Country/Territory	United States
City	Farmington
Period	6/06/17 → 9/06/17

Bibliographical note

Publisher Copyright:
© 2019, Springer International Publishing AG, part of Springer Nature.

Keywords

Adaptive virtual agents
Empathetic robots
Personality recognition

Access to Document

10.1007/978-3-319-92108-2_13

Cite this

Kampman, O., Siddique, F. B., Yang, Y., & Fung, P. (2019). Adapting a virtual agent to user personality. In L. Devillers, M. Eskenazi, & J. Mariani (Eds.), Advanced Social Interaction with Agents - 8th International Workshop on Spoken Dialog Systems (pp. 111-118). (Lecture Notes in Electrical Engineering; Vol. 510). Springer Verlag. https://doi.org/10.1007/978-3-319-92108-2_13

@inproceedings{91005033fd1e4c72b493e9b815c83838,

title = "Adapting a virtual agent to user personality",

abstract = "We propose to adapt a virtual agent called {\textquoteleft}Zara the Supergirl{\textquoteright} to user personality. User personality is deducted through two models, one based on raw audio and the other based on speech transcription text. Both models show good performance, with an average F-score of 69.6 for personality perception from audio, and an average F-score of 71.0 for recognition from text. Both models deploy a Convolutional Neural Network. Through a Human-Agent Interaction study we find correlations between user personality and preferred agent personality. The study suggests that especially the Openness user personality trait correlates with a stronger preference for agents with more gentle personality. People also sense more empathy and enjoy better conversations when agents adapt their personalities.",

keywords = "Adaptive virtual agents, Empathetic robots, Personality recognition",

author = "Onno Kampman and Siddique, \{Farhad Bin\} and Yang Yang and Pascale Fung",

note = "Publisher Copyright: {\textcopyright} 2019, Springer International Publishing AG, part of Springer Nature.; 8th International Workshop on Spoken Dialogue Systems, IWSDS 2017 ; Conference date: 06-06-2017 Through 09-06-2017",

year = "2019",

doi = "10.1007/978-3-319-92108-2\_13",

language = "English",

isbn = "9783319921075",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "111--118",

editor = "Laurence Devillers and Maxine Eskenazi and Joseph Mariani",

booktitle = "Advanced Social Interaction with Agents - 8th International Workshop on Spoken Dialog Systems",

}

Kampman, O, Siddique, FB, Yang, Y & Fung, P 2019, Adapting a virtual agent to user personality. in L Devillers, M Eskenazi & J Mariani (eds), Advanced Social Interaction with Agents - 8th International Workshop on Spoken Dialog Systems. Lecture Notes in Electrical Engineering, vol. 510, Springer Verlag, pp. 111-118, 8th International Workshop on Spoken Dialogue Systems, IWSDS 2017, Farmington, United States, 6/06/17. https://doi.org/10.1007/978-3-319-92108-2_13

Adapting a virtual agent to user personality. / Kampman, Onno; Siddique, Farhad Bin; Yang, Yang et al.
Advanced Social Interaction with Agents - 8th International Workshop on Spoken Dialog Systems. ed. / Laurence Devillers; Maxine Eskenazi; Joseph Mariani. Springer Verlag, 2019. p. 111-118 (Lecture Notes in Electrical Engineering; Vol. 510).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Adapting a virtual agent to user personality

AU - Kampman, Onno

AU - Siddique, Farhad Bin

AU - Yang, Yang

AU - Fung, Pascale

PY - 2019

Y1 - 2019

N2 - We propose to adapt a virtual agent called ‘Zara the Supergirl’ to user personality. User personality is deducted through two models, one based on raw audio and the other based on speech transcription text. Both models show good performance, with an average F-score of 69.6 for personality perception from audio, and an average F-score of 71.0 for recognition from text. Both models deploy a Convolutional Neural Network. Through a Human-Agent Interaction study we find correlations between user personality and preferred agent personality. The study suggests that especially the Openness user personality trait correlates with a stronger preference for agents with more gentle personality. People also sense more empathy and enjoy better conversations when agents adapt their personalities.

AB - We propose to adapt a virtual agent called ‘Zara the Supergirl’ to user personality. User personality is deducted through two models, one based on raw audio and the other based on speech transcription text. Both models show good performance, with an average F-score of 69.6 for personality perception from audio, and an average F-score of 71.0 for recognition from text. Both models deploy a Convolutional Neural Network. Through a Human-Agent Interaction study we find correlations between user personality and preferred agent personality. The study suggests that especially the Openness user personality trait correlates with a stronger preference for agents with more gentle personality. People also sense more empathy and enjoy better conversations when agents adapt their personalities.

KW - Adaptive virtual agents

KW - Empathetic robots

KW - Personality recognition

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:000559129600013

UR - https://openalex.org/W2736494118

UR - https://www.scopus.com/pages/publications/85051783599

U2 - 10.1007/978-3-319-92108-2_13

DO - 10.1007/978-3-319-92108-2_13

M3 - Conference Paper published in a book

SN - 9783319921075

T3 - Lecture Notes in Electrical Engineering

SP - 111

EP - 118

BT - Advanced Social Interaction with Agents - 8th International Workshop on Spoken Dialog Systems

A2 - Devillers, Laurence

A2 - Eskenazi, Maxine

A2 - Mariani, Joseph

PB - Springer Verlag

T2 - 8th International Workshop on Spoken Dialogue Systems, IWSDS 2017

Y2 - 6 June 2017 through 9 June 2017

ER -

Adapting a virtual agent to user personality

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this