Sciweavers

Share
ECLIPSE
2007
ACM

Predicting buggy changes inside an integrated development environment

9 years 2 months ago
Predicting buggy changes inside an integrated development environment
We present a tool that predicts whether the software under development inside an IDE has a bug. An IDE plugin performs this prediction, using the Change Classification technique to classify source code changes as buggy or clean during the editing session. Change Classification uses Support Vector Machines (SVM), a machine learning classifier algorithm, to classify changes to projects mined from their configuration management repository. This technique, besides being language independent and relatively accurate, can (a) classify a change immediately upon its completion and (b) use features extracted solely from the change delta (added, deleted) and the source code to predict buggy changes. Thus, integrating change classification within an IDE can predict potential bugs in the software as the developer edits the source code, ideally reducing the amount of time spent on fixing bugs later. To this end, we have developed a Change Classification plugin for Eclipse based on client-server arc...
Janaki T. Madhavan, E. James Whitehead Jr.
Added 14 Aug 2010
Updated 14 Aug 2010
Type Conference
Year 2007
Where ECLIPSE
Authors Janaki T. Madhavan, E. James Whitehead Jr.
Comments (0)
books