Expanding the capabilities of a bug report annotation tool for summarization
No Thumbnail Available
Date
2024
Authors
Devaiya, Shraddhaben Nareshbhai
University of Lethbridge. Faculty of Arts and Science
Journal Title
Journal ISSN
Volume Title
Publisher
Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science
Abstract
Bug reports serve as critical communication channels between users and software developers,
conveying information about unexpected issues or flaws within a software system.
Sometimes developers or triagers need to spend significant time understanding a long and
complex bug report. A bug report summarizer streamlines the bug triage process for software
developers by condensing complex bug reports into concise and informative summaries,
facilitating efficient issue prioritization and resolution. To cater comments to the
need of the developer for the complex bug report, prior work suggested the solution of
annotation of bug report comments. Though the developed annotator worked well, it had
issues with annotating the description and off-topic labels. Other prior work identified fiftyone
patterns to detect planning in bug report comments. We used these phrases to create an
annotated dataset of bug report sentences for plan intention research. In this research, we
improve the annotation capabilities of the description and off-topic labeler and automate
the plan labeler using a supervised machine-learning approach.
Description
Keywords
bug reports , bug report summarization , annotation tool , plan labeler , off-topic labeler , description labeler , machine learning model