It's Not a Bug, It's a Feature: How Misclassification Impacts Bug Prediction
- ICSE 2013
by
Kim Herzig, Sascha Just, Andreas Zeller
ICSE '13: Proceedings of the 2013 International Conference on Software Engineering, Pages 392-401, IEEE Press, June 2013.
ISBN: 978-1-4673-3076-3
Abstract
In a manual examination of more than 7,000 issue reports from the bug databases of five open-source projects, we found 33.8% of all bug reports to be misclassified?that is, rather than referring to a code fix, they resulted in a new feature, an update to documentation, or an internal refactoring. This misclassification introduces bias in bug prediction models, confusing bugs and features: On average, 39% of files marked as defective actually never had a bug. We discuss the impact of this misclassification on earlier studies and recommend manual data validation for future studies.
BibTeX Entry
@inproceedings{herzig-icse-2013, title = "It's Not a Bug, It's a Feature: How Misclassification Impacts Bug Prediction", author = "Kim Herzig and Sascha Just and Andreas Zeller", year = "2013", month = jun, booktitle = "ICSE '13: Proceedings of the 2013 International Conference on Software Engineering", location = "San Fancisco, CA, USA", pages = "392--401", publisher = "IEEE Press", ISBN = "978-1-4673-3076-3", }