It’s Not a Bug, It’s a Feature: How Misclassification Impacts Bug Prediction

TitleIt’s Not a Bug, It’s a Feature: How Misclassification Impacts Bug Prediction
Publication TypeConference Proceedings
Year of Publication2013
AuthorsHerzig, Kim, Just Sascha, and Zeller Andreas
Refereed DesignationRefereed
Secondary Title35th Int'l Conference on Software Engineering (ICSE 2013)
Pagination392-401
Date Published05/2013
Keywordsbias, bug reports, data quality, mining software repositories, noise
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.