Call Center Stress Recognition with Person-Specific Models

  • Javier Hernandez
  • Rob R. Morris
  • Rosalind W. Picard
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6974)


Nine call center employees wore a skin conductance sensor on the wrist for a week at work and reported stress levels of each call. Although everyone had the same job profile, we found large differences in how individuals reported stress levels, with similarity from day to day within the same participant, but large differences across the participants. We examined two ways to address the individual differences to automatically recognize classes of stressful/non-stressful calls, namely modifying the loss function of Support Vector Machines (SVMs) to adapt to the varying priors, and giving more importance to training samples from the most similar people in terms of their skin conductance lability. We tested the methods on 1500 calls and achieved an accuracy across participants of 78.03% when trained and tested on different days from the same person, and of 73.41% when trained and tested on different people using the proposed adaptations to SVMs.


Stress recognition skin conductance interpersonal variability Support Vector Machines Affective Computing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Barreto, A., Zhai, J., Adjouadi, M.: Non-intrusive physiological monitoring for automated stress detection in human-computer interaction. In: ICCV-HCI, pp. 29–38 (2007)Google Scholar
  2. 2.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: 5th Annual ACM workshop on Computational Learning Theory, pp. 144–152. ACM Press, New York (1992)Google Scholar
  3. 3.
    Boucsein, W.: Electrodermal Activity. Plenum Press, New York (1992)CrossRefGoogle Scholar
  4. 4.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines (2001), software
  5. 5.
    Crider, A.: Personality and electrodermal response lability: an interpretation. Applied Psychophysiol Biofeedback 33(3), 141–148 (2008)CrossRefGoogle Scholar
  6. 6.
    Healey, J.A., Picard, R.W.: Detecting stress during real-world driving tasks using physiological sensors. IEEE Trans. Intell. Transport. Syst. 6, 156–166 (2005)CrossRefGoogle Scholar
  7. 7.
    Huang, Y.M., Du, S.X.: Weighted support vector machine for classification with uneven training class sizes. In: 4th International Conference on Machine Learning and Cybernetics, vol. 7, pp. 4365–4369. IEEE Press, Los Alamitos (2005)Google Scholar
  8. 8.
    Cacioppo, J.T., Tassinary, L.G., Berntson, G.G.: Handbook of Psychophysiology. Cambridge University Press, Cambridge (2000)Google Scholar
  9. 9.
    Kelsey, R.M.: Electrodermal lability and myocardial reactivity to stress. Psychophysiology 28(6), 619–631 (1991)CrossRefGoogle Scholar
  10. 10.
    Lunn, D., Harper, S.: Using galvanic skin response measures to identify areas of frustration for older web 2.0 users. In: International Cross Disciplinary Conference on Web Accessibility, p. 34. ACM, New York (2010)Google Scholar
  11. 11.
    Lykken, D.T., Venables, P.H.: Direct measurement of skin conductance: A proposal for standarization. Psychophysiology 8(5), 656–672 (1971)CrossRefGoogle Scholar
  12. 12.
    Mundy-Castle, A.C., McKiever, B.L.: The psychophysiological significance of the galvanic skin response. Experimental Psychology 46(1), 15–24 (1953)CrossRefGoogle Scholar
  13. 13.
    Poh, M., Swenson, N., Picard, R.: A wearable sensor for unobtrusive, long-term assessment of electrodermal activity. IEEE Trans. Biomed. Eng. 57(5), 1243–1252 (2010)CrossRefGoogle Scholar
  14. 14.
    Setz, C., Arnrich, B., Schumm, J., La Marca, R., Troster, G., Ehlert, U.: Discriminating stress from cognitive load using a wearable eda device. IEEE Transactions on Information Technology in Biomedicine 14(2), 410–417 (2010)CrossRefGoogle Scholar
  15. 15.
    Shi, Y., Nguyen, M.H., Blitz, P., French, B., Fisk, S., De la Torre, F., Smailagic, A., Siewiorek, D.P., al’ Absi, M., Ertin, E., Kamarck, T., Kumar, S.: Personalized stress detection from physiological measurements. In: International Symposium on Quality of Life Technology (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Javier Hernandez
    • 1
  • Rob R. Morris
    • 1
  • Rosalind W. Picard
    • 1
  1. 1.Media LabMassachussets Institute of TechnologyCambridgeUSA

Personalised recommendations