Avoiding Bias in Students’ Intrinsic Motivation Detection

  • Pedro Bispo SantosEmail author
  • Caroline Verena Bhowmik
  • Iryna Gurevych
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12149)


Intrinsic motivation is the psychological construct that defines our reasons and interests to perform a set of actions. It has shown to be associated with positive outcomes across domains, especially in the academic context. Therefore, understanding and identifying peoples’ levels of intrinsic motivation can be crucial for professionals of many domains, e.g. teachers aiming to offer better support to students’ learning processes and enhance their academic outcomes. In a first attempt to tackle this issue, we propose an end-to-end approach for recognition of intrinsic motivation, using only facial expressions as input. Our results show that visual cues from students’ facial expressions are an important source of information to detect their levels of intrinsic motivation (AUC \(=0.570\), \(F_1=0.556\)). We also show how to avoid potential bias that might be present in datasets. When dividing the training samples per gender, we achieved a substantial improvement for both genders (AUC \(=0.739\) and \(F_1=0.852\) for male students, AUC \(=0.721\) and \(F_1=0.723\) for female students).


Affective computing Fairness in AI Behavioral analytics Facial expressions Intrinsic motivation Nonverbal signals Educational psychology 


  1. 1.
    Azevedo, R., Millar, G., Taub, M., Mudrick, N., Bradbury, A., Price, M.: Using data visualizations to foster emotion regulation during self-regulated learning with advanced learning technologies: a conceptual framework. In: International Learning Analytics and Knowledge Conference, Vancouver, BC, Canada, pp. 444–448 (2017)Google Scholar
  2. 2.
    Deci, E.: Intrinsic motivation, extrinsic reinforcement, and inequity. J. Pers. Soc. Psychol. 22(1), 113–120 (1972)CrossRefGoogle Scholar
  3. 3.
    D’Mello, S., Craig, S., Witherspoon, A., McDaniel, B., Graesser, A.: Automatic detection of learner’s affect from conversational cues. User Model. User-Adap. Interact. 18(1–2), 45–80 (2008). Scholar
  4. 4.
    D’Mello, S., Graesser, A.: Automatic detection of learner’s affect from gross body language. Appl. Artif. Intell. 23(2), 123–150 (2009)CrossRefGoogle Scholar
  5. 5.
    D’Mello, S., Graesser, A.: Mind and body: dialogue and posture for affect detection in learning environments. In: International Conference on Artificial Intelligence in Education, Los Angeles, CA, USA, pp. 161–168 (2007)Google Scholar
  6. 6.
    Dwork, C., Immorlica, N., Kalai, A.T., Leiserson, M.: Decoupled classifiers for group-fair and efficient machine learning. In: Proceedings of the 1st Conference on Fairness, Accountability and Transparency, New York, NY, USA, vol. 81, pp. 119–133 (2018)Google Scholar
  7. 7.
    Frey, A., et al. (eds.): PISA 2006 Handbook of Scales. Documentation of Assessment Instruments (PISA 2006 Skalenhandbuch. Dokumentation der Erhebungsinstrumente). Waxmann (2009)Google Scholar
  8. 8.
    Johnson, W.L., Lester, J.C.: Face-to-face interaction with pedagogical agents, twenty years later. Int. J. Artif. Intell. Educ. 26(1), 25–36 (2015). Scholar
  9. 9.
    Kaur, A., Mustafa, A., Mehta, L., Dhall, A.: Prediction and localization of student engagement in the wild. CoRR abs/1804.00858 (2018)Google Scholar
  10. 10.
    Maehr, M.L., Meyer, H.A.: Understanding motivation and schooling: where we’ve been, where we are, and where we need to go. Educ. Psychol. Rev. 9(4), 371–409 (1997). Scholar
  11. 11.
    Monkaresi, H., Bosch, N., Calvo, R., D’Mello, S.: Automated detection of engagement using video-based estimation of facial expressions and heart rate. IEEE Trans. Affect. Comput. 8(1), 15–28 (2017)CrossRefGoogle Scholar
  12. 12.
    Rotgans, J., Schmidt, H.: Situational interest and academic achievement in the active-learning classroom. Learn. Instr. 21(1), 58–67 (2011)CrossRefGoogle Scholar
  13. 13.
    Ryu, H., Mitchell, M., Adam, H.: Improving smiling detection with race and gender diversity. CoRR abs/1712.00193 (2017).
  14. 14.
    Schiefele, U.: Interest, learning, and motivation. Educ. Psychol. 26(3–4), 299–323 (1991)CrossRefGoogle Scholar
  15. 15.
    de Vicente, A., Pain, H.: Motivation diagnosis in intelligent tutoring systems. In: Goettl, B.P., Halff, H.M., Redfield, C.L., Shute, V.J. (eds.) ITS 1998. LNCS, vol. 1452, pp. 86–95. Springer, Heidelberg (1998). Scholar
  16. 16.
    de Vicente, A., Pain, H.: Informing the detection of the students’ motivational state: an empirical study. In: Cerri, S.A., Gouardères, G., Paraguaçu, F. (eds.) ITS 2002. LNCS, vol. 2363, pp. 933–943. Springer, Heidelberg (2002). Scholar
  17. 17.
    Whitehill, J., Serpell, Z., Lin, Y.C., Foster, A., Movellan, J.R.: The faces of engagement: automatic recognition of student engagement from facial expressions. IEEE Trans. Affect. Comput. 5(1), 86–98 (2014)CrossRefGoogle Scholar
  18. 18.
    Zhao, J., Wang, T., Yatskar, M., Ordonez, V., Chang, K.W.: Men also like shopping: reducing gender bias amplification using corpus-level constraints. In: Empirical Methods in Natural Language Processing. pp. 2979–2989. Copenhagen, Denmark (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Pedro Bispo Santos
    • 1
    Email author
  • Caroline Verena Bhowmik
    • 2
  • Iryna Gurevych
    • 1
  1. 1.Ubiquitous Knowledge Processing (UKP) LabDarmstadtGermany
  2. 2.Department of PsychologyUniversity of Koblenz-LandauKoblenzGermany

Personalised recommendations