The Problem Solving Genome: Analyzing Sequential Patterns of Student Work with Parameterized Exercises

Parameterized exercises are an important tool for online assessment and learning. The ability to generate multiple versions of the same exercise with different parameters helps to support learning-by-doing and decreases cheating during assessment. At the same time, our experience using parameterized exercises for Java programming reveals suboptimal use of this technology as demonstrated by repeated successful and failed attempts to solve the same problem. In this paper we present the results of our work on modeling and examining patterns of student behavior with parameterized exercises using the Problem Solving Genome, a compact encapsulation of individual behavior patterns. We started with micro-patterns (genes) that describe small chunks of repetitive behavior and constructed individual genomes as frequency profiles that show the dominance of each gene in individual behavior. The exploration of student genomes revealed the individual genome is considerably stable, distinguishing students from their peers. Using the genome, we were able to analyze student behavior on the group level and identify genes associated with good and poor learning performance.

[1]  D. Schunk,et al.  Risk Taking: Theoretical, Empirical, and Educational Considerations , 1991 .

[2]  D. McAdams.  What Do We Know When We Know a Person , 1995 .

[3]  B. Weiner.  An attributional theory of motivation and emotion , 1986 .

[4]  G. Kortemeyer,et al.  Experiences using the open-source learning content management and assessment system LON-CAPA in introductory physics courses , 2008 .

[5]  R. Mayer.  Cognitive, metacognitive, and motivational aspects of problem solving , 1998 .

[6]  Edwin Kashy,et al.  Using networked tools to enhance student success rates in large classes , 1997, Proceedings Frontiers in Education 1997 27th Annual Conference. Teaching and Learning in an Era of Change.

[7]  Gautam Biswas,et al.  Identifying Students' Characteristic Learning Behaviors in an Intelligent Tutoring System Fostering Self-Regulated Learning , 2012, EDM.

[8]  Vladimir Zadorozhny,et al.  Re-assessing the Value of Adaptive Navigation Support in E-Learning Context , 2008, AH.

[9]  Ulrike von Luxburg,et al.  A tutorial on spectral clustering , 2007, Stat. Comput..

[10]  G. Albertelli,et al.  Individualized interactive exercises: A promising role for network technology , 2001 .

[11]  Peter Brusilovsky,et al.  Motivational Social Visualizations for Personalized E-Learning , 2012, EC-TEL.

[12]  Johannes Gehrke,et al.  Sequential PAttern mining using a bitmap representation , 2002, KDD.

[13]  Sanjay Chawla,et al.  Sequential Pattern Mining with Constraints on Large Protein Databases , 2005, COMAD.

[14]  Judy Kay,et al.  Analysing Frequent Sequential Patterns of Collaborative Learning Activity Around an Interactive Tabletop. Nominee for Best Paper Award , 2010, EDM.

[15]  Peter Brusilovsky,et al.  Adaptive Navigation Support for Parameterized Questions in Object-Oriented Programming , 2009, EC-TEL.

[16]  Gautam Biswas,et al.  Identifying Learning Behaviors by Contextualizing Differential Sequence Mining with Action Features and Performance Evolution , 2012, EDM.

[17]  Peter Brusilovsky,et al.  Individualized exercises for self-assessment of programming knowledge: An evaluation of QuizPACK , 2005, JERC.

[18]  John S. Kinnebrew,et al.  A Contextualized, Differential Sequence Mining Method to Derive Students' Learning Behavior Patterns , 2013, EDM 2013.

[19]  Thomas F. Stahovich,et al.  Differential Pattern Mining of Students' Handwritten Coursework , 2013, EDM.

[20]  Manolis Mavrikis,et al.  Proceedings of the 7th International Conference on Educational Data Mining. , 2014, EDM 2014.