Multistrategy discovery and detection of novice programmer errors

College

College of Computer Studies

Department/Unit

Computer Science

Document Type

Article

Source Title

Machine Learning

Volume

38

First Page

157

Last Page

180

Publication Date

2000

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.

html

Disciplines

Computer Sciences

Keywords

Intelligent tutoring systems; Error-correcting codes (Information theory)

Upload File

wf_no

This document is currently not available here.

Share

COinS