Home // ACHI 2012, The Fifth International Conference on Advances in Computer-Human Interactions // View article

Emotion Recognition Through ANS Responses Evoked by Negative Emotions

Authors:
Eun-Hye Jang
Byoung-Jun Park
Yeongji Eum
Sang-Hyeob Kim
Chul Huh
Jin-Hun Sohn

Keywords: emotion recognition; machine learning algorithm; ANS responses

Abstract:
Emotion recognition using physiological responses is one of the core processes to implement emotional intelligence in human-computer interaction (HCI) research. The purpose of this study was to investigate emotion-specific ANS responses and test recognition rate using classification algorithm when negative emotion such as fear, surprise, and stress was evoked. The results of one-way ANOVA toward each parameter, there were significant differences among three emotions in skin conductance response (SCR), number of SCR (NSCR), skin temperature (SKT), and high frequency of HRV (HF). Results of emotion recognition applied to statistical method, i.e. linear discriminant analysis (LDA) and 4 machine learning algorithm, i.e. classification and regression tree (CART), self organizing map (SOM), Naïve Bayes and support vector machine (SVM) for emotion recognition showed that an accuracy of emotion classification by SVM was the highest and by LDA was the lowest. This can be helpful to provide the basis for the emotion recognition technique in HCI as well as contribute to the standardization in emotion-specific ANS responses.

Pages: 218 to 223

Copyright: Copyright (c) IARIA, 2012

Publication date: January 30, 2012

Published in: conference

ISSN: 2308-4138

ISBN: 978-1-61208-177-9

Location: Valencia, Spain

Dates: from January 30, 2012 to February 4, 2012