Considering the Influence of Prerequisite Performance on Wheel Spinning

The phenomenon of wheel spinning refers to students attempting to solve problems on a particular skill, but becoming stuck due to an inability to learn the skill. Past research has found that students who do not master a skill quickly tend not to master it at all. One question is why do students wheel spin? A plausible hypothesis is that students become stuck on a skill because they do not understand the necessary prerequisite knowledge, and so are unable to learn the current skill. We analyzed data from the ASSISTments system, and determined the impact of how student performance on prerequisite skills influenced ability to learn postrequisite skills. We found a strong gradient with respect to knowledge of prerequisites: students in the bottom 20% of pre-required knowledge exhibited wheel spinning behavior 50% of the time, while those in the top 20% of pre-required knowledge exhibited wheel spinning behavior only 10% of the time. This information is a statistically reliable predictor, and considering it results in a modest improvement in our ability to detect wheel spinning behaviors: R2 improves from 0.264 to 0.268, and AUC improves from 0.884 to 0.888.

[1]  P. Fayers.  Item Response Theory for Psychologists , 2004, Quality of Life Research.

[2]  Kenneth R. Koedinger,et al.  Performance Factors Analysis - A New Alternative to Knowledge Tracing , 2009, AIED.

[3]  Emma Brunskill.  Estimating Prerequisite Structure From Noisy Data , 2011, EDM.

[4]  Peter Brusilovsky,et al.  General Features in Knowledge Tracing to Model Multiple Subskills, Temporal Item Response Theory, and Expert Knowledge , 2014, EDM.

[5]  Tristan Nixon,et al.  A Method for Finding Prerequisites Within a Curriculum , 2011, EDM.

[6]  Yue Gong,et al.  Wheel-Spinning: Students Who Fail to Master a Skill , 2013, AIED.

[7]  Neil T. Heffernan,et al.  The impact of gaming ( ? ) on learning at the fine-grained level , 2010 .

[8]  Ryan Shaun Joazeiro de Baker,et al.  Towards Automatically Detecting Whether Student Learning is Shallow , 2012, International Journal of Artificial Intelligence in Education.

[9]  Ryan Shaun Joazeiro de Baker,et al.  Developing a generalizable detector of when students game the system , 2008, User Modeling and User-Adapted Interaction.

[10]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[11]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[12]  John R. Anderson,et al.  Knowledge tracing: Modeling the acquisition of procedural knowledge , 2005, User Modeling and User-Adapted Interaction.

[13]  Kenneth R. Koedinger,et al.  Using Item-type Performance Covariance to Improve the Skill Model of an Existing Tutor , 2008, EDM.

[14]  Ricardo Conejo,et al.  Introducing Prerequisite Relations in a Multi-layered Bayesian Student Model , 2005, User Modeling.

[15]  Yue Gong,et al.  Towards Detecting Wheel-Spinning: Future Failure in Mastery Learning , 2015, L@S.

[16]  Neil T. Heffernan,et al.  The Prediction of Student First Response Using Prerequisite Skills , 2015, L@S.

[17]  Beverly Park Woolf,et al.  Inferring learning and attitudes from a Bayesian Network of log file data , 2005, AIED.

[18]  Joseph E. Beck,et al.  Understanding Wheel Spinning in the Context of Affective Factors , 2014, Int. J. People Oriented Program..