Replication Kit: "Skill Models for Programming Language Concepts"

<strong>Structure</strong> <strong>data</strong>: contains the data we used for our case study <strong>pfa</strong>: data sets generated from the raw data in the database <strong>raw</strong>: raw data collected in SmartAPE [1] containing the source code of the students as well as the assessment results of the system <strong>similarity</strong>: calculated similarities between solutions for each level and each exercise <strong>results</strong>: contains the complete results of our case study <strong>krms</strong>: Knowlede Requirements Models for each exercise and each KC level in .graphml format. You can use yEd [2] to visualize them. <strong>pfa_metrics</strong>: Results of AUC, Gmean and MCC for each of our PFA model configurations in .csv and .Rda format <strong>similarities</strong>: plotly [3] graphics of our similarity results in .html format calculation scripts: <strong>similarities.R</strong>: script used to generate box plots of similarities. Uses data from <em>data/similarities</em> as input <strong>pfa_trainer.R</strong>: script to fit different configurations of PFA models and test them using different performance metrics. Uses <em>data/pfa</em> as input <strong>comparison.R</strong>: script that performs statistical tests to compate different PFA configurations. Uses <em>results/pfa_metrics/results.Rda</em> as input <strong>References</strong> [1] Albrecht, Ella et al. “Experiences in Introducing Blended Learning in an Introductory Programming Course.” <em>ECSEE</em> (2018). [2] yEd - Graph editor. https://www.yworks.com/products/yed [3] plotly. https://plot.ly