SMELL AWARE BUG CLASSIFICATION

Code smell indicates inadequacies in design and implementation choices. Code smellsnegative impact on software maintainability including effects on components’ bugproneness and code quality have been demonstrated in previous studies. This study aimsto investigate the importance of code smell metrics in prediction models for detectingbug-prone code modules. For improvement of the bug prediction model, in this study,smell-based metrics of code have been used. For the training of our model, weemployed 14 different open-source projects from the promise repository. Every projectfile consists of source code as well as smell code metrics and was written in Java. Weexamined different evaluation metrics such as F1_score, accuracy, precision, recall,area under the receiver operating characteristic curve, and area under the precision-recall curveof the five methods within the version, within the project, and across the projects.We classify the code components as buggy or non-buggy using Naïve Bayes, RandomForest (RF), Support Vector Machine (SVM), Logistic Regression, and k-NearestNeighbor classifiers. RF and SVM have given better results within the version andwithin the project.