Multistrategy Discovery and Detection of Novice Programmer Errors
Abstract
Detecting and diagnosing errors in novice behavior is an important student modeling task. In this paper, we describe MEDD, an unsupervised incremental multistrategy system for the discovery of classes of errors from, and their detection in, novice programs. Experimental results show that MEDD can effectively detect and discover misconceptions and other knowledge-level errors that underlie novice Prolog programs, even when multiple errors are enmeshed together in a single program, and when the programs are presented to MEDD in a different order.
Cite
Text
Sison et al. "Multistrategy Discovery and Detection of Novice Programmer Errors." Machine Learning, 2000. doi:10.1023/A:1007690108308Markdown
[Sison et al. "Multistrategy Discovery and Detection of Novice Programmer Errors." Machine Learning, 2000.](https://mlanthology.org/mlj/2000/sison2000mlj-multistrategy/) doi:10.1023/A:1007690108308BibTeX
@article{sison2000mlj-multistrategy,
title = {{Multistrategy Discovery and Detection of Novice Programmer Errors}},
author = {Sison, Raymund and Numao, Masayuki and Shimura, Masamichi},
journal = {Machine Learning},
year = {2000},
pages = {157-180},
doi = {10.1023/A:1007690108308},
volume = {38},
url = {https://mlanthology.org/mlj/2000/sison2000mlj-multistrategy/}
}