Using Feature Selection and Unsupervised Clustering to Identify Affective Expressions in Educational Games

Educational games can induce a wide range of emotions, and so recognizing specific emotions may be valuable for an intelligent system that aims to adapt to varying student needs so as to improve learning. The long-term goal of this work is to understand how user affect impacts overall learning in an educational game. The main contribution of this paper is an investigation into the use of an unsupervised machine learning technique to help recognize meaningful patterns in biometric affective data. Results show that this method can identify interesting and sensible student reactions to different game events.

[1]  Cristina Conati,et al.  Modelling Learning in an Educational Game , 2005, AIED.

[2]  Ashish Kapoor,et al.  Multimodal affect recognition in learning environments , 2005, ACM Multimedia.

[3]  Jennifer Healey,et al.  Detecting stress during real-world driving tasks using physiological sensors , 2005, IEEE Transactions on Intelligent Transportation Systems.

[4]  Ruth Aylett,et al.  Socially Intelligent Agents - Creating Relationships with Computers and Robots , 2003, J. Documentation.

[5]  Cristina Conati,et al.  Data-Driven Refinement of a Probabilistic Model of User Affect , 2005, User Modeling.

[6]  Anil K. Jain,et al.  Data clustering: a review , 1999, CSUR.

[7]  P. Ekman,et al.  Autonomic nervous system activity distinguishes among emotions. , 1983, Science.

[8]  Christine L. Lisetti,et al.  Using Noninvasive Wearable Computers to Recognize Human Emotions from Physiological Signals , 2004, EURASIP J. Adv. Signal Process..

[9]  Cristina Conati,et al.  Automatic Recognition of Learner Groups in Exploratory Learning Environments , 2006, Intelligent Tutoring Systems.

[10]  Cristina Conati,et al.  Socially Intelligent Agents in Educational Games , 2002 .

[11]  Rosalind W. Picard,et al.  Expression glasses: a wearable device for facial expression recognition , 1999, CHI Extended Abstracts.

[12]  Regan L. Mandryk,et al.  Using psychophysiological techniques to measure user experience with entertainment technologies , 2006, Behav. Inf. Technol..

[13]  Cristina Conati,et al.  A Study on Using Biometric Sensors for Monitoring User Emotions in Educational Games , 2003 .

[14]  J. Friedman,et al.  Clustering objects on subsets of attributes (with discussion) , 2004 .

[15]  J. Friedman.  Clustering objects on subsets of attributes , 2002 .

[16]  M. Bradley,et al.  Looking at pictures: affective, facial, visceral, and behavioral reactions. , 1993, Psychophysiology.

[17]  Cristina Conati.  How to Evaluate Models of User Affect? , 2004, ADS.