A Model of Affect and Learning for Intelligent Tutors

A model of affect and learning for intelligent tutoring systems is proposed. The model considers both how a student feels and what a student knows, and then customizes how instruction is presented and how learning and performance are reinforced. The model was designed based on teachers’ expertise, which was obtained through interviews and interaction with an educational game on number factorization learning. The core of the model is a dynamic decision network, which generates tutorial actions balancing affect and knowledge. The student’s affect representation relies on a Bayesian network and theoretical models of emotion and personality. A controlled user study to evaluate the impact of the model on learning was performed. Current results are encouraging since they show significant improvement in learning when the model of affect and learning is incorporated.

[1]  Jannica Heinström,et al.  From Fear to Flow , 2010 .

[2]  Arthur C. Graesser,et al.  AutoTutor and affective autotutor: Learning by talking with cognitively and emotionally intelligent computers that talk back , 2012, TIIS.

[3]  Cristina Conati,et al.  Knowledge Elicitation Methods for Affect Modelling in Education , 2013, Int. J. Artif. Intell. Educ..

[4]  James C. Lester,et al.  Affect and Engagement in Game-BasedLearning Environments , 2014, IEEE Transactions on Affective Computing.

[5]  Judith Good,et al.  Exploring affective technologies for the classroom with the subtle stone , 2010, CHI.

[6]  Cristina Conati,et al.  Empirically building and evaluating a probabilistic model of user affect , 2009, User Modeling and User-Adapted Interaction.

[7]  Roy C. Milton,et al.  An Extended Table of Critical Values for the Mann-Whitney (Wilcoxon) Two-Sample Statistic , 1964 .

[8]  R. Calvo,et al.  New Perspectives on Affect and Learning Technologies , 2011 .

[9]  M. Pett Nonparametric Statistics for Health Care Research: Statistics for Small Samples and Unusual Distributions , 1997 .

[10]  P. Costa,et al.  Four ways five factors are basic , 1992 .

[11]  Benedict du Boulay,et al.  Designing Affective and Cognitive Educational Interaction , 2013 .

[12]  Beverly Park Woolf,et al.  Actionable Affective Processing for Automatic Tutor Interventions , 2011 .

[13]  Claude Frasson,et al.  Virtual Environment for Monitoring Emotional Behaviour in Driving , 2014, Intelligent Tutoring Systems.

[14]  L. Enrique Sucar,et al.  Affective Modeling for an Intelligent Educational Environment , 2013 .

[15]  John Benedict du Boulay Towards a Motivationally Intelligent Pedagogy: How Should an Intelligent Tutor Respond to the Unmotivated or the Demotivated? , 2011 .

[16]  M. Guha The Sage Encyclopedia of Social Science Research Methods , 2005 .

[17]  A. Damasio,et al.  We feel, therefore we learn: The relevance of affective and social neuroscience to education. , 2007 .

[18]  Ryan Shaun Joazeiro de Baker,et al.  Sensor-Free Affect Detection for a Simulation-Based Science Inquiry Learning Environment , 2014, Intelligent Tutoring Systems.

[19]  Cristina Conati,et al.  An Analysis of Attention to Student - Adaptive Hints in an Educational Game , 2012, ITS.

[20]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[21]  Jamshid Shanbehzadeh,et al.  EVE: AN AFFECT-SENSITIVE PEDAGOGICAL AGENT , 2014 .

[22]  Kasia Muldner,et al.  The Impact of Animated Pedagogical Agents on Girls' and Boys' Emotions, Attitudes, Behaviors and Learning , 2011, 2011 IEEE 11th International Conference on Advanced Learning Technologies.

[23]  Kurt VanLehn,et al.  A System Architecture for Affective Meta Intelligent Tutoring Systems , 2014, Intelligent Tutoring Systems.

[24]  Arthur C. Graesser,et al.  Multimodal semi-automated affect detection from conversational cues, gross body language, and facial features , 2010, User Modeling and User-Adapted Interaction.

[25]  D. Laplane Thought and language. , 1992, Behavioural neurology.