Abstract
In this chapter, we present an approach to modeling user affect that combines explicit information on both causes of emotional reaction (expressed in terms of cognitive appraisal theory) and effects of such reactions (detected via philological sensors). One advantage of this approach is that using both sources increases model accuracy. As second advantage is that, by assessing not only which emotions the user is feeling but also why they arise, this model enhances a system’s ability to adequately respond to these emotions. We first describe the general approach and its theoretical underpinnings. We then introduce the general steps needed to build an affective user model following our approach, and discuss how these steps were implemented to build the affective model for Prime Climb, a user-adaptive educational game for math. We conclude by reporting results on an empirical evaluation of the model.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Currently, the dialog box only elicits information on emotions towards the game and the agent because dealing with three pairs of emotions turned out to be too overwhelming for students.
References
Conati, C. (2002). Probabilistic assessment of user’s emotions in educational games. Journal of Applied Artificial Intelligence, 16(7–8), 555–575.
Conati, C. (2004). How to evaluate models of user affect? In In Elisabeth André, Laila Dybkjær, Wolfgang Minker, & Paul Heisterkamp (Eds.),Proceedings of ADS’04, Tutorial and Research Workshop on Affective Dialog Systems. (pp. 288–300), Kloster Irsee, Germany.
Conati, C., & Maclaren, H. (2009a). Empirically building and evaluating a probabilistic model of user affect. User Modeling and User-Adapted Interaction, 19(3), 267–303.
Conati, C., & Maclaren, H. (2009b). Modeling user affect from causes and effects. In Proceedings of UMAP 2009, First and Seventeenth International Conference on User Modeling, Adaptation and Personalization. pp 4–15. Springer, LNCS 5535.
Conati, C., & Manske, M. (2009). Evaluating adaptive feedback in an educational computer game. In Hannes Högni Viljálmsson (Eds.), Proceedings of Intelligent Virtual Agents (IVA) 2009 (pp. 146–158). Amsterdam, The Netherlands: Springer, LNCS 5773.
Cooper, D., Muldner, K., Arroyo, I., Park Woolf, B., & Burleson, W. (2010). Ranking feature sets for emotion models used in classroom based intelligent tutoring systems. In P. De Bra, A. Kobsa, & D. Chin (Eds.), Proceedings of UMAP 2010 (pp. 135–146). Big Island, HI, USA: Springer, LNCS 6075.
Costa, P. T., & McCrae, R. R. (1992). Four ways five factors are basic. Personality and Individual Differences, 13, 653–665.
D’Mello, S., & Graesser, A. C. (2010). Multimodal semi-automated affect detection from conversational cues, gross body language, and facial features. User Modeling and User-Adapted Interaction, 20(2), 147–187.
de Castell, S., & Jenson, J. (2007). Digital games for education: When meanings play. Intermedialities, 9, 45–54.
Gee, J. P. (2003). What video games have to teach us about learning and literacy. New York: Palgrave Macmillan.
Graziano, W. G., Jensen-Campbell, L. A., & Finch, J. F. (1997). The self as a mediator between personality and adjustment. Journal of Personality and Social Psychology, 73, 392–404.
Healey, J. A., & Picard, R. W. (2005). Detecting stress during real-world driving tasks using physiological sensors. IEEE Transactions on Intelligent Transportation Systems, 6(2), 156–166.
Lang, P., Greenwald, M., Bradley, M., & Hamm, A. (1993). Look at pictures: Affective, facial, visceral, and behavioral reactions. Psychophysiology, 30, 261–273.
Litman, D. J., & Forbes-Riley, K. (2004). Predicting student emotions in computer-human tutoring dialogues. In Donia Scott (Ed.), 42nd Annual Meeting of the Association for Computational Linguistics (ACL) (pp. 352–359). Barcelona, Spain.
Manske, M., & Conati, C. (2005). Modelling learning in educational games. Proceedings of the 12th International Conference on AI in Education. Amsterdam, The Netherlands.
Ortony, A., Clore, G. L., & Collins, A. (1988). The cognitive structure of emotion. New York: Cambridge University Press.
Prendinger, H., Mori, J., & Ishizuka, M. (2005). Recognizing, modeling, and responding to users’ affective states. In Liliana Ardissono, Paul Brna & Antonija Mitrovic (Eds.), UM’05 10th International Conference on User Modeling. (pp. 60–69). Edinburgh, UK. Springer, LNCS 3538.
Zhou, X., & Conati, C. (2003). Inferring user goals from personality and behavior in a causal model of user affect. In Johnson, Lewis & Andre, Elisabeth (Eds.), IUI’03, International Conference on Intelligent User Interfaces (pp. 211–218). Miami, FL.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Conati, C. (2011). Combining Cognitive Appraisal and Sensors for Affect Detection in a Framework for Modeling User Affect. In: Calvo, R., D'Mello, S. (eds) New Perspectives on Affect and Learning Technologies. Explorations in the Learning Sciences, Instructional Systems and Performance Technologies, vol 3. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-9625-1_6
Download citation
DOI: https://doi.org/10.1007/978-1-4419-9625-1_6
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4419-9624-4
Online ISBN: 978-1-4419-9625-1
eBook Packages: Humanities, Social Sciences and LawEducation (R0)