The Problem Solving Genome: Analyzing Sequential Patterns of Student Work with Parameterized Exercises
Julio Guerra, Shaghayegh Sahebi, Yu‐Ru Lin, Peter L. Brusilovsky · D-Scholarship@Pitt (University of Pittsburgh) · 2014
Parameterized exercises are an important tool for online as-sessment and learning. The ability to generate multiple ver-sions 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 param-eterized exercises for Java programming reveals suboptimal use of this technology as demonstrated by repeated success-ful 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 en-capsulation of individual behavior patterns. We started with micro-patterns (genes) that describe small chunks of repet-itive behavior and constructed individual genomes as fre-quency profiles that show the dominance of each gene in individual behavior. The exploration of student genomes revealed the individual genome is considerably stable, dis-tinguishing 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. Categories and Subject Descriptors