Code smell detection and identification in imbalanced environments

作者：

Highlights：

• Code smells detection could be an imbalanced data classification problem.

• The existing works have encountered problems in dealing with data imbalance.

• A novel approach called ADIODE is proposed to detect and/or identify code smells.

• An experimental study is performed using the F-measure and the AUC metrics.

摘要

•Code smells detection could be an imbalanced data classification problem.•The existing works have encountered problems in dealing with data imbalance.•A novel approach called ADIODE is proposed to detect and/or identify code smells.•An experimental study is performed using the F-measure and the AUC metrics.

论文关键词：Code smells detection,Smell type identification,Imbalanced data classification,Oblique decision tree,Evolutionary algorithm

论文评审过程：Received 19 October 2019, Revised 28 September 2020, Accepted 29 September 2020, Available online 1 October 2020, Version of Record 7 October 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114076