Towards the improvement of self-service systems via emotional virtual agents

Christopher J. Martin, Leslie D. Ball, Jacqueline Archibald, Lloyd Carson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Downloads (Pure)

Abstract

Affective computing and emotional agents have been found to have a positive effect on human-computer interactions. In order to develop an acceptable emotional agent for use in a self-service interaction, two stages of research were identified and carried out; the first to determine which facial expressions are present in such an interaction and the second to determine which emotional agent behaviours are perceived as appropriate during a problematic self-service shopping task. In the first stage, facial expressions associated with negative affect were found to occur during self-service shopping interactions, indicating that facial expression detection is suitable for detecting negative affective states during self-service interactions. In the second stage, user perceptions of the emotional facial expressions displayed by an emotional agent during a problematic self-service interaction were gathered. Overall, the expression of disgust was found to be perceived as inappropriate while emotionally neutral behaviour was perceived as appropriate, however gender differences suggested that females perceived surprise as inappropriate. Results suggest that agents should change their behaviour and appearance based on user characteristics such as gender.
Original languageEnglish
Title of host publicationProceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers
Place of PublicationSwindon
PublisherBCS Learning & Development Ltd.
Pages351-356
Number of pages6
Publication statusPublished - 10 Sep 2012
Event26th Annual BCS Interaction Specialist Group Conference on People and Computers - Birmingham, United Kingdom
Duration: 10 Sep 201214 Sep 2012
Conference number: 26

Conference

Conference26th Annual BCS Interaction Specialist Group Conference on People and Computers
Abbreviated titleBCS-HCI '12
CountryUnited Kingdom
CityBirmingham
Period10/09/1214/09/12
OtherThis year's conference returns to its foundation theme of 'People and Computers', and so has attracted a wide range of HCI work. The BCS Conference on Human Computer Interaction is the leading conference of its type in the UK and is one of the top European conferences in the field. It performs a critical role in supporting the development and success of the UK HCI community. As such, the conference aims to provide opportunities for open dialogue and academic debate that is inclusive of our entire community.

This ethos is reflected in these proceedings, which represent a body of work we hope will broaden your thoughts, develop your ideas, and deepen your understanding of state of the art HCI research.

Fingerprint

Emotion
Interaction
Service system
Shopping
Negative affect
Disgust
Gender differences
Human-computer interaction
Behavior change
Surprise

Cite this

Martin, C. J., Ball, L. D., Archibald, J., & Carson, L. (2012). Towards the improvement of self-service systems via emotional virtual agents. In Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers (pp. 351-356). Swindon: BCS Learning & Development Ltd..
Martin, Christopher J. ; Ball, Leslie D. ; Archibald, Jacqueline ; Carson, Lloyd. / Towards the improvement of self-service systems via emotional virtual agents. Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers. Swindon : BCS Learning & Development Ltd., 2012. pp. 351-356
@inproceedings{05f723b98e9947c38b5f14e80e1909ed,
title = "Towards the improvement of self-service systems via emotional virtual agents",
abstract = "Affective computing and emotional agents have been found to have a positive effect on human-computer interactions. In order to develop an acceptable emotional agent for use in a self-service interaction, two stages of research were identified and carried out; the first to determine which facial expressions are present in such an interaction and the second to determine which emotional agent behaviours are perceived as appropriate during a problematic self-service shopping task. In the first stage, facial expressions associated with negative affect were found to occur during self-service shopping interactions, indicating that facial expression detection is suitable for detecting negative affective states during self-service interactions. In the second stage, user perceptions of the emotional facial expressions displayed by an emotional agent during a problematic self-service interaction were gathered. Overall, the expression of disgust was found to be perceived as inappropriate while emotionally neutral behaviour was perceived as appropriate, however gender differences suggested that females perceived surprise as inappropriate. Results suggest that agents should change their behaviour and appearance based on user characteristics such as gender.",
author = "Martin, {Christopher J.} and Ball, {Leslie D.} and Jacqueline Archibald and Lloyd Carson",
year = "2012",
month = "9",
day = "10",
language = "English",
pages = "351--356",
booktitle = "Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers",
publisher = "BCS Learning & Development Ltd.",

}

Martin, CJ, Ball, LD, Archibald, J & Carson, L 2012, Towards the improvement of self-service systems via emotional virtual agents. in Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers. BCS Learning & Development Ltd., Swindon, pp. 351-356, 26th Annual BCS Interaction Specialist Group Conference on People and Computers, Birmingham, United Kingdom, 10/09/12.

Towards the improvement of self-service systems via emotional virtual agents. / Martin, Christopher J.; Ball, Leslie D.; Archibald, Jacqueline; Carson, Lloyd.

Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers. Swindon : BCS Learning & Development Ltd., 2012. p. 351-356.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Towards the improvement of self-service systems via emotional virtual agents

AU - Martin, Christopher J.

AU - Ball, Leslie D.

AU - Archibald, Jacqueline

AU - Carson, Lloyd

PY - 2012/9/10

Y1 - 2012/9/10

N2 - Affective computing and emotional agents have been found to have a positive effect on human-computer interactions. In order to develop an acceptable emotional agent for use in a self-service interaction, two stages of research were identified and carried out; the first to determine which facial expressions are present in such an interaction and the second to determine which emotional agent behaviours are perceived as appropriate during a problematic self-service shopping task. In the first stage, facial expressions associated with negative affect were found to occur during self-service shopping interactions, indicating that facial expression detection is suitable for detecting negative affective states during self-service interactions. In the second stage, user perceptions of the emotional facial expressions displayed by an emotional agent during a problematic self-service interaction were gathered. Overall, the expression of disgust was found to be perceived as inappropriate while emotionally neutral behaviour was perceived as appropriate, however gender differences suggested that females perceived surprise as inappropriate. Results suggest that agents should change their behaviour and appearance based on user characteristics such as gender.

AB - Affective computing and emotional agents have been found to have a positive effect on human-computer interactions. In order to develop an acceptable emotional agent for use in a self-service interaction, two stages of research were identified and carried out; the first to determine which facial expressions are present in such an interaction and the second to determine which emotional agent behaviours are perceived as appropriate during a problematic self-service shopping task. In the first stage, facial expressions associated with negative affect were found to occur during self-service shopping interactions, indicating that facial expression detection is suitable for detecting negative affective states during self-service interactions. In the second stage, user perceptions of the emotional facial expressions displayed by an emotional agent during a problematic self-service interaction were gathered. Overall, the expression of disgust was found to be perceived as inappropriate while emotionally neutral behaviour was perceived as appropriate, however gender differences suggested that females perceived surprise as inappropriate. Results suggest that agents should change their behaviour and appearance based on user characteristics such as gender.

M3 - Conference contribution

SP - 351

EP - 356

BT - Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers

PB - BCS Learning & Development Ltd.

CY - Swindon

ER -

Martin CJ, Ball LD, Archibald J, Carson L. Towards the improvement of self-service systems via emotional virtual agents. In Proceedings of the 26th Annual BCS Interaction Specialist Group Conference on People and Computers. Swindon: BCS Learning & Development Ltd. 2012. p. 351-356