The working group will conduct a systematic literature review based on the guidelines proposed by Kitchenham et al. It is therefore timely to conduct and present such a review in order to gain an understanding of the research focuses, to highlight advances in knowledge since 2003, and to indicate possible future directions for research. There does not appear to have been a comprehensive review of research into introductory programming since that of Robins et al. Some notable areas that have not been reviewed are assessment, academic integrity, and novice student attitudes to programming. While these aspects encompass a wide range of issues, they do not cover the full scope of research into novice programming. However, these reviews have focused on highly specific aspects, such as student misconceptions, teaching approaches, program comprehension, potentially seminal papers, research methods applied, automated feedback for exercises, competency-enhancing games, and program visualisation. Since this work there have been several reviews of research concerned with the teaching and learning of programming, in particular introductory programming. Based on these results we present a generic predictive model and its potential application as an early warning system for early identification of students at risk.Ī broad review of research on the teaching and learning of programming was conducted by Robins et al. The prediction accuracy in identifying at-risk students on unknown data for the course was 71% (overall prediction accuracy) in compliance with the area under the curve (ROC) score (0.66). The models that used in-class assessment and cognitive features as predictors returned best at-risk prediction accuracies, compared with models that used take-home assessment and cognitive features as predictors. Our analysis revealed that the use of just three variables was a good fit for the models employed. The models use formative assessment tasks and self-reported cognitive features such as prior programming knowledge and problem-solving skills. This paper presents a class of machine learning predictive models based on Naive Bayes classification, to predict student performance in introductory programming. Predictive models may serve as early warning systems to identify students at risk of failing or quitting early. Among these include the development of effective predictive models to predict student academic performance.
The pursuit of a deeper understanding of factors that influence student performance outcomes has long been of interest to the computing education community.
0 kommentar(er)
