TY - GEN
T1 - Enhancing Code Smell Detection Performance in Python Programming Language
T2 - 2nd IEEE International Conference on Electrical Engineering, Computer and Information Technology, ICEECIT 2024
AU - Retnani, Windi Eka Yulia
AU - Siahaan, Daniel
AU - Bukhori, Saiful
AU - Dharmawan, Tio
AU - Bayu, Johar
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Code smell is one of the problems in programming which indicates that a problem has occurred, where there is something less than ideal in the code even though the code can run well. This research conducted a comparative study of the performance of Decision Tree, Random Forest, the use of the AdaBoost, CatBoost, XGBoost ensemble, and the use of SMOTEENN preprocessing to improve code smell detection in the Python programming language. Overall, the Decision Tree Pruning model hybrid with Adaboost and SMOTEEN produces the highest accuracy of 98.69% and MCC of 97.40%. Meanwhile, on the Long Method dataset, the XGBoost model with the SMOTEENN application produces the highest accuracy of 99.69% and MCC of 99.38%.
AB - Code smell is one of the problems in programming which indicates that a problem has occurred, where there is something less than ideal in the code even though the code can run well. This research conducted a comparative study of the performance of Decision Tree, Random Forest, the use of the AdaBoost, CatBoost, XGBoost ensemble, and the use of SMOTEENN preprocessing to improve code smell detection in the Python programming language. Overall, the Decision Tree Pruning model hybrid with Adaboost and SMOTEEN produces the highest accuracy of 98.69% and MCC of 97.40%. Meanwhile, on the Long Method dataset, the XGBoost model with the SMOTEENN application produces the highest accuracy of 99.69% and MCC of 99.38%.
KW - Code Smell
KW - Large Class
KW - Long Methode
KW - Machine Learning
KW - Python
UR - https://www.scopus.com/pages/publications/85218107699
U2 - 10.1109/ICEECIT63698.2024.10859904
DO - 10.1109/ICEECIT63698.2024.10859904
M3 - Conference contribution
AN - SCOPUS:85218107699
T3 - ICEECIT 2024 - Proceedings: 2nd International Conference on Electrical Engineering, Computer and Information Technology 2024
SP - 354
EP - 359
BT - ICEECIT 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 22 November 2024 through 23 November 2024
ER -