Visualization of Student Activity Patterns within Intelligent Tutoring Systems

Novel and simplified methods for determining low-level states of student behavior and predicting affective states enable tutors to better respond to students. The Many Eyes Word Tree graphics is used to understand and analyze sequential patterns of student states, categorizing raw quantitative indicators into a limited number of discrete sates. Used in combination with sensor predictors, we demonstrate that a combination of features, automatic pattern discovery and feature selection algorithms can predict and trace higher-level states (emotion) and inform more effective real-time tutor interventions.

[1]  Sidney K. D'Mello,et al.  Monitoring Affect States During Effortful Problem Solving Activities , 2010, Int. J. Artif. Intell. Educ..

[2]  Allan Wigfield,et al.  Risk Taking: Theoretical, Empirical, and Educational Considerations , 1991 .

[3]  Kurt VanLehn,et al.  The Andes Physics Tutoring System: Lessons Learned , 2005, Int. J. Artif. Intell. Educ..

[4]  Kristy Elizabeth Boyer,et al.  Predicting Facial Indicators of Confusion with Hidden Markov Models , 2011, ACII.

[5]  Eamonn J. Keogh,et al.  Probabilistic discovery of time series motifs , 2003, KDD '03.

[6]  Kristy Elizabeth Boyer,et al.  Characterizing the Effectiveness of Tutorial Dialogue with Hidden Markov Models , 2010, Intelligent Tutoring Systems.

[7]  Arthur C. Graesser,et al.  AUTOMATIC DETECTION OF LEARNER'S AFFECT FROM GROSS BODY LANGUAGE , 2009, Appl. Artif. Intell..

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

[9]  Paul R. Cohen,et al.  Temporal Data Mining for Educational Applications , 2008, Int. J. Softw. Informatics.

[10]  Jeremy Buhler,et al.  Finding motifs using random projections , 2001, RECOMB.

[11]  Ronald H. Stevens,et al.  Modeling the Development of Problem Solving Skills in Chemistry with a Web-Based Tutor , 2004, Intelligent Tutoring Systems.

[12]  Beverly Park Woolf,et al.  Effort-based Tutoring: An Empirical Approach to Intelligent Tutoring , 2010, EDM.

[13]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[14]  Jessica Lin,et al.  Finding Motifs in Time Series , 2002, KDD 2002.

[15]  Arthur C. Graesser,et al.  Modeling Cognitive-Affective Dynamics with Hidden Markov Models , 2010 .

[16]  Beverly Park Woolf,et al.  Web-Based Intelligent Multimedia Tutoring for High Stakes Achievement Tests , 2004, Intelligent Tutoring Systems.

[17]  Paul Brna,et al.  User Modeling 2005, 10th International Conference, UM 2005, Edinburgh, Scotland, UK, July 24-29, 2005, Proceedings , 2005, User Modeling.

[18]  Beverly Park Woolf,et al.  A Dynamic Mixture Model to Detect Student Motivation and Proficiency , 2006, AAAI.

[19]  Cynthia Breazeal,et al.  Affective Learning — A Manifesto , 2004 .

[20]  Joseph E. Beck,et al.  Engagement tracing: using response times to model student disengagement , 2005, AIED.

[21]  Jeremy Buhler,et al.  Finding Motifs Using Random Projections , 2002, J. Comput. Biol..

[22]  Ryan Shaun Joazeiro de Baker,et al.  Detecting When Students Game the System, Across Tutor Subjects and Classroom Cohorts , 2005, User Modeling.

[23]  Beverly Park Woolf,et al.  Identifying High-Level Student Behavior Using Sequence-based Motif Discovery , 2010, EDM.

[24]  R. Calvo,et al.  Significant Accomplishments, New Challenges, and New Perspectives , 2011 .

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