An automatically classified dataset of configuration bug reports for Eclipse projects.

This dataset is the result of an automated classification project. We used a fine-tuned model (ModernBERT) to classify bug reports into configuration related bug reports or not configuration related. The dataset consist of 301,465 bug reports with the following attributes:Bug-ID, Project, Summary, Description, Link, Enviroment, Tags, Dataset, text_combined, predicted_label_index, predicted_label