I got sick in San Francisco. Kim jumped in at the last a second and gave the presentation at ICSE 2013. He did a great job in presenting our work in the grand ballroom. We got a lot of good questions and discussions going after the presentation. Thanks to everyone who attended the session.

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

Kim Herzig, Sascha Just and Andreas Zeller

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 issue 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 estimate the impact of this misclassification on earlier studies and recommend manual data validation for future studies.

No Comment

You can post first response comment.

Leave A Comment

Please enter your name. Please enter an valid email address. Please enter a message.