An analysis of patterns of debugging among novice computer science students
ITiCSE '05 Proceedings of the 10th annual SIGCSE conference on Innovation and technology in computer science education
Introduction to Data Mining, (First Edition)
Introduction to Data Mining, (First Edition)
Journal of Systems and Software
The impacts of function extraction technology on program comprehension: A controlled experiment
Information and Software Technology
Education: Alice 3: concrete to abstract
Communications of the ACM - A Blind Person's Interaction with Technology
An evaluation framework for plagiarism detection
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Posters
WEKA---Experiences with a Java Open-Source Project
The Journal of Machine Learning Research
Personifying programming tool feedback improves novice programmers' learning
Proceedings of the seventh international workshop on Computing education research
Advances and Challenges in Log Analysis
Queue - Log Analysis
Hi-index | 0.00 |
Designing an experiment for programming education research, in which collecting and interpreting a large number of qualitative data about programmers is required, needs careful consideration in order to validate the experiment. When it comes to finding a pattern in the programming behaviour of a specific group of programmers (e,g. novice, intermediate or expert programmers), one of the critical issues is the selection of similar participants who can be placed in one group. In this study we were interested in finding a method that could shorten the path to finding participants. Therefore, the use of clustering algorithms to group similar participants was put to test in order to investigate the effectiveness and feasibility of this approach. The clustering algorithms that were used for this study were K-means and DBSCAN. The results showed that the use of these algorithms, for the mentioned purpose, is feasible and that both algorithms can identify similar participants and place them in the same group while participants who are not similar to others, and therefore are not the correct subject of the study, are recognised.