Skip to main content

Learning to decode human emotions from event-related potentials


Reported works on electroencephalogram (EEG)-based emotion recognition systems generally employ the principles of supervised learning to build subject-dependent (single/intra-subject) models. Building subject-independent (multiple/inter-subject) models is a harder problem due to the EEG data variability between subjects. The contribution of this paper is twofold. First, we provide a framework for selection of a small number of basic temporal features, event-related potential (ERP) amplitudes, and latencies that are sufficiently robust to discriminate emotion states across multiple subjects. Second, we test comparatively the feasibility of six standard unsupervised (clustering) techniques to build intra-subject and inter-subject models to discriminate emotion valence in the ERPs collected while subjects were viewing high arousal images with positive or negative emotional content.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2


  1. 1.

    Calvo RA, D’Mello SK (2010) Affect detection: an interdisciplinary review of models, methods, and their applications. IEEE Trans Affect Comput 1(1):18–37

    Article  Google Scholar 

  2. 2.

    Dalgleish T, Dunn B, Mobbs D (2009) Affective neuroscience: past, present, and future. Emot Rev 1:355–368

    Article  Google Scholar 

  3. 3.

    Olofsson JK, Nordin S, Sequeira H, Polich J (2008) Affective picture processing: an integrative review of ERP findings. Biol Psychol 77:247–265

    Article  Google Scholar 

  4. 4.

    AlZoubi O, Calvo RA, Stevens RH (2009) Classification of EEG for emotion recognition: an adaptive approach. In: Proceedings of the 22nd Australasian joint conference. Artificial intelligence, pp 52–61

  5. 5.

    Petrantonakis PC, Hadjileontiadis LJ (2010) Emotion recognition from EEC using higher order crossings. IEEE Trans Inf Technol Biomed 14(2):186–194

    Article  Google Scholar 

  6. 6.

    Jatupaiboon N, Panngum S, Israsena P (2013) Real-time EEG-based happiness detection system. Sci World J 2013. Article ID 618649, 12 p

  7. 7.

    Lin YP, Wang CH, Wu TL, Jeng SK, Chen JH (2008) Support vector machine for EEG signal classification during listening to emotional music. In: Proceedings of the 10th IEEE workshop on multimedia signal processing, (MMSP’08), 127–130, Cairns, Australia, Oct 2008

  8. 8.

    Li M, Lu B-L (2009) Emotion classification based on gamma-band EEG. 31st annual international conference of the IEEE EMBS Minneapolis, Minnesota, USA, September 2–6, 2009, pp 1323–1326

  9. 9.

    Nie D, Wang X-W, Shi L-C, Lu B-L (2011) EEG-based emotion recognition during watching movies. Proceedings of the 5th international IEEE EMBS conference on neural engineering, Cancun, Mexico, pp 667–670, April 27–May 1, 2011

  10. 10.

    Chanel G, Kronegg J, Grandjean D, Pun T (2006) Emotion assessment: arousal evaluation using EEG’s and peripheral physiological signals. In: Gunsel B, Jain A, Tekalp AM, Sankur B (eds) Multimedia content representation, classification and security, vol 4105. Springer, Berlin, pp 530–537

  11. 11.

    Frantzidis Ch A, Bratsas Ch, Klados MA, Konstantinidis E, Lithari ChD, Vivas AB, Papadelis Ch L, Kaldoudi E, Pappas C, Bamidis PD (2010) On the classification of emotional biosignals evoked while viewing affective pictures: an integrated data-mining-based approach for healthcare applications. IEEE Trans Inf Technol Biomed 14(2):309

    Article  Google Scholar 

  12. 12.

    Bos D (2007) EEG-based emotion recognition.

  13. 13.

    Tomé AM, Hidalgo-Munoz AR, Pérez ML, Teixeira AR, Santos IM, Pereira AT, Vázquez-Marrufo M, Lang EW (2013) Feature extraction and classification of biosignals emotion valence detection from EEG signals. BIOSIGNALS 2013, international conference on bio-inspired systems and signal processing, Barcelona, February 2013

  14. 14.

    Liu Y, Sourina O, Nguyen MK (2010) Real-time EEG-based human emotion recognition and visualization. In: Proceedings of the international conference on cyberworlds (CW’10), pp 262–269, Singapore, October 2010

  15. 15.

    Georgieva O, Milanov S, Georgieva P (2013) Cluster analysis for EEG biosignal discrimination. IEEE international symposium on innovations in intelligent systems and applications INISTA, Albena, Bulgaria, 19–21 June 2013

  16. 16.

    Santos IM, Iglesias J, Olivares EI, Young AW (2008) Differential effects of object-based attention on evoked potentials to fearful and disgusted faces. Neuropsychologia 46:1468–1479

    Article  Google Scholar 

  17. 17.

    Pourtois G, Grandjean D, Sander D, Vuilleumier P (2004) Electrophysiological correlates of rapid spatial orienting towards fearful faces. Cereb Cortex 14(6):619–633

    Article  Google Scholar 

  18. 18.

    Hall M (1999) Correlation-based feature selection for machine learning. PhD thesis, Department of Computer Science, University of Waikato, New Zealand

  19. 19.

    Ladha L, Deepa T (2011) Feature selection methods and algorithms. Int J Comput Sci Eng (IJCSE) 3(5):1787–1797

    Google Scholar 

  20. 20.

    Stolarova M, Keil A, Moratti S (2006) Modulation of the C1 visual event-related component by conditioned stimuli: evidence for sensory plasticity in early affective perception. Cereb Cortex 16:876–887

    Article  Google Scholar 

  21. 21.

    Milanov S, Georgieva O, Georgieva P (2013) Comparative analysis of brain data clustering. In: Proceedings of doctoral conference in mathematics, informatics and education, Sofia, Bulgaria, pp 94–101, 19–29 September

  22. 22.

    Java Machine Learning Library.

  23. 23.

    Waikato Environment for Knowledge Analysis (WEKA).

  24. 24.

    Gianotti LRR, Faber PL, Schuler M, Pascual-Marqui RD, Kochi K, Lehmann D (2008) First valence, then arousal: the temporal dynamics of brain electric activity evoked by emotional stimuli. Brain Topogr 20:143–156

    Article  Google Scholar 

  25. 25.

    Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York

    Book  MATH  Google Scholar 

  26. 26.

    Cuthbert BN, Schupp HT, Bradley MM, Birbaumer N, Lang PJ (2000) Brain potentials in affective picture processing: covariation with autonomic arousal and affective report. Biol Psychol 52:95–111

    Article  Google Scholar 

  27. 27.

    Karegowda AG, Manjunath AS, Jayaram MA (2010) Comparative study of attribute selection using gain ratio and correlation based feature selection. Int J Inf Technol Knowl Manag 2(2):271–277

    Google Scholar 

Download references


The work was supported partially by the project “Data mining methods for development and assessment of software services,” 2014 of Science Fund of SU “Kl. Ohridski.” It was also supported by the bilateral student Erasmus program between University of Aveiro, Portugal, and Sofia University “St. Kl. Ohridski,” Bulgaria.

Author information



Corresponding author

Correspondence to P. Georgieva.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Georgieva, O., Milanov, S., Georgieva, P. et al. Learning to decode human emotions from event-related potentials. Neural Comput & Applic 26, 573–580 (2015).

Download citation


  • Affective computing
  • Emotion valence recognition
  • Feature reduction
  • Clustering
  • Event-related potentials (ERPs)