Human Rating of Emotional Expressions - Scales vs. Preferences

Marco Pasch, Andrea Kleinsmith, Monica Landoni

2014

Abstract

Human ratings of emotional expressions are the foundation for building and training automatic affect recognition systems. We compare two rating schemes for labeling emotional expressions: likert scales and pair-wise preferences. A statistical analysis shows that while there is a strong correlation between the two schemes, there are also frequent mismatches. Our findings indicate that the schemes perform differently well per affect label. We discuss reasons for this and outline planned future work based on the findings.

References

  1. Afzal, S. and Robinson, P. (2009). Natural affect data: Collection and annotation in a learning context. In Affective Computing and Intelligent Interaction and Workshops, 2009. ACII 2009. 3rd International Conference on, pages 1-7.
  2. Doyle, J. (2004). Prospects for preferences. Computational Intelligence, 20(2):111-136.
  3. Fürnkranz, J. and Hüllermeier, E. (2005). Preference learning. Künstliche Intelligenz, 19(1):60-61.
  4. Kapoor, A., Burleson, W., and Picard, R. W. (2007). Automatic prediction of frustration. Int. J. Hum.-Comput. Stud., 65(8):724-736.
  5. Kleinsmith, A. and Bianchi-Berthouze, N. (2013). Affective body expression perception and recognition: A survey. Affective Computing, IEEE Transactions on, 4(1):15-33.
  6. Kleinsmith, A., Bianchi-Berthouze, N., and Steed, A. (2011). Automatic recognition of non-acted affective postures. Trans. Sys. Man Cyber. Part B, 41(4):1027- 1038.
  7. Kleinsmith, A., De Silva, P. R., and Bianchi-Berthouze, N. (2006). Cross-cultural differences in recognizing affect from body posture. Interact. Comput., 18(6):1371-1389.
  8. Liscombe, J., Venditti, J., and Hirschberg, J. (2003). Classifying subject ratings of emotional speech using acous-
Download


Paper Citation


in Harvard Style

Pasch M., Landoni M. and Kleinsmith A. (2014). Human Rating of Emotional Expressions - Scales vs. Preferences . In Proceedings of the International Conference on Physiological Computing Systems - Volume 1: PhyCS, ISBN 978-989-758-006-2, pages 240-245. DOI: 10.5220/0004727602400245


in Bibtex Style

@conference{phycs14,
author={Marco Pasch and Monica Landoni and Andrea Kleinsmith},
title={Human Rating of Emotional Expressions - Scales vs. Preferences},
booktitle={Proceedings of the International Conference on Physiological Computing Systems - Volume 1: PhyCS,},
year={2014},
pages={240-245},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004727602400245},
isbn={978-989-758-006-2},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Physiological Computing Systems - Volume 1: PhyCS,
TI - Human Rating of Emotional Expressions - Scales vs. Preferences
SN - 978-989-758-006-2
AU - Pasch M.
AU - Landoni M.
AU - Kleinsmith A.
PY - 2014
SP - 240
EP - 245
DO - 10.5220/0004727602400245