• Skip to main content
  • Skip to header left navigation
  • Skip to site footer
This website is moving.


  • Newsletters
  • About
  • Courses
  • Free Course Materials
    • Basic Intro to Game Design
    • How to Write CHI Papers
  • Log In
The Acagamic

The Acagamic

User Experience Research & Design in Games

You are here: Home / Publications / A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers

A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers

May 20, 2022 by

by Pedro A Nogueira, Rui A Rodrigues, Eugénio Oliveira, Lennart E Nacke
Abstract:
With the rising popularity of affective computing techniques, there have been several advances in the field of emotion recognition systems. However, despite the several advances in the field, these systems still face scenario adaptability and practical implementation issues. In light of these issues, we developed a nonspecific method for emotional state classification in interactive environments. The proposed method employs a two-layer classification process to detect Arousal and Valence (the emotion’s hedonic component), based on four psychophysiological metrics: Skin Conductance, Heart Rate and Electromyography measured at the corrugator supercilii and zygomaticus major muscles. The first classification layer applies multiple regression models to correctly scale the aforementioned metrics across participants and experimental conditions, while also correlating them to the Arousal or Valence dimensions. The second layer then explores several machine learning techniques to merge the regression outputs into one final rating. The obtained results indicate we are able to classify Arousal and Valence independently from participant and experimental conditions with satisfactory accuracy (97% for Arousal and 91% for Valence).
View PDF
Reference:
A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers (Pedro A Nogueira, Rui A Rodrigues, Eugénio Oliveira, Lennart E Nacke), In Proceedings of IEEE/WIC/ACM Conference on Web Intelligence 2013, IEEE, volume 2, 2013.
Bibtex Entry:
@inproceedings{nogueira2013hybrid,
abstract = {With the rising popularity of affective computing techniques, there have been several advances in the field of emotion recognition systems. However, despite the several advances in the field, these systems still face scenario adaptability and practical implementation issues. In light of these issues, we developed a nonspecific method for emotional state classification in interactive environments. The proposed method employs a two-layer classification process to detect Arousal and Valence (the emotion’s hedonic component), based on four psychophysiological metrics: Skin Conductance, Heart Rate and Electromyography measured at the corrugator supercilii and zygomaticus major muscles. The first classification layer applies multiple regression models to correctly scale the aforementioned metrics across participants and experimental conditions, while also correlating them to the Arousal or Valence dimensions. The second layer then explores several machine learning techniques to merge the regression outputs into one final rating. The obtained results indicate we are able to classify Arousal and Valence independently from participant and experimental conditions with satisfactory accuracy (97% for Arousal and 91% for Valence).},
address = {Atlanta, GA, United States},
author = {Nogueira, Pedro A and Rodrigues, Rui A and Oliveira, Eug'{e}nio and Nacke, Lennart E},
booktitle = {Proceedings of IEEE/WIC/ACM Conference on Web Intelligence 2013},
doi = {10.1109/WI-IAT.2013.117},
organization = {IEEE},
pages = {253--260},
publisher = {IEEE},
title = {{A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers}},
url = {http://paginas.fe.up.pt/~niadr/PUBLICATIONS/2013/2013_IAT.pdf},
volume = {2},
year = {2013}
}

The public part of this work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International LicenseCC-BY-NC-ND 4.0 license, all paid parts are copyright by Lennart Nacke · The Acagamic · Privacy Policy