Saved in:
Bibliographic Details
Main Authors: Van Petegem, Charlotte, Demeyere, Kasper, Maertens, Rien, Strijbol, Niko, De Wever, Bram, Mesuere, Bart, Dawyndt, Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.01579
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909188185128960
author Van Petegem, Charlotte
Demeyere, Kasper
Maertens, Rien
Strijbol, Niko
De Wever, Bram
Mesuere, Bart
Dawyndt, Peter
author_facet Van Petegem, Charlotte
Demeyere, Kasper
Maertens, Rien
Strijbol, Niko
De Wever, Bram
Mesuere, Bart
Dawyndt, Peter
contents In programming education, providing manual feedback is essential but labour-intensive, posing challenges in consistency and timeliness. We introduce ECHO, a machine learning method to automate the reuse of feedback in educational code reviews by analysing patterns in abstract syntax trees. This study investigates two primary questions: whether ECHO can predict feedback annotations to specific lines of student code based on previously added annotations by human reviewers (RQ1), and whether its training and prediction speeds are suitable for using ECHO for real-time feedback during live code reviews by human reviewers (RQ2). Our results, based on annotations from both automated linting tools and human reviewers, show that ECHO can accurately and quickly predict appropriate feedback annotations. Its efficiency in processing and its flexibility in adapting to feedback patterns can significantly reduce the time and effort required for manual feedback provisioning in educational settings.
format Preprint
id arxiv_https___arxiv_org_abs_2405_01579
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Mining patterns in syntax trees to automate code reviews of student solutions for programming exercises
Van Petegem, Charlotte
Demeyere, Kasper
Maertens, Rien
Strijbol, Niko
De Wever, Bram
Mesuere, Bart
Dawyndt, Peter
Software Engineering
Computers and Society
Machine Learning
In programming education, providing manual feedback is essential but labour-intensive, posing challenges in consistency and timeliness. We introduce ECHO, a machine learning method to automate the reuse of feedback in educational code reviews by analysing patterns in abstract syntax trees. This study investigates two primary questions: whether ECHO can predict feedback annotations to specific lines of student code based on previously added annotations by human reviewers (RQ1), and whether its training and prediction speeds are suitable for using ECHO for real-time feedback during live code reviews by human reviewers (RQ2). Our results, based on annotations from both automated linting tools and human reviewers, show that ECHO can accurately and quickly predict appropriate feedback annotations. Its efficiency in processing and its flexibility in adapting to feedback patterns can significantly reduce the time and effort required for manual feedback provisioning in educational settings.
title Mining patterns in syntax trees to automate code reviews of student solutions for programming exercises
topic Software Engineering
Computers and Society
Machine Learning
url https://arxiv.org/abs/2405.01579