Comparing heuristic and machine learning approaches for metric-based code smell detection

F Pecorelli, F Palomba, D Di Nucci… - 2019 IEEE/ACM 27th …, 2019 - ieeexplore.ieee.org
Code smells represent poor implementation choices performed by developers when
enhancing source code. Their negative impact on source code maintainability and …

Machine learning techniques for code smell detection: A systematic literature review and meta-analysis

MI Azeem, F Palomba, L Shi, Q Wang - Information and Software …, 2019 - Elsevier
Background: Code smells indicate suboptimal design or implementation choices in the
source code that often lead it to be more change-and fault-prone. Researchers defined …

Code smell detection by deep direct-learning and transfer-learning

T Sharma, V Efstathiou, P Louridas… - Journal of Systems and …, 2021 - Elsevier
Context: An excessive number of code smells make a software system hard to evolve and
maintain. Machine learning methods, in addition to metric-based and heuristic-based …

Detecting code smells using machine learning techniques: Are we there yet?

D Di Nucci, F Palomba, DA Tamburri… - 2018 ieee 25th …, 2018 - ieeexplore.ieee.org
Code smells are symptoms of poor design and implementation choices weighing heavily on
the quality of produced source code. During the last decades several code smell detection …

On the role of data balancing for machine learning-based code smell detection

F Pecorelli, D Di Nucci, C De Roover… - Proceedings of the 3rd …, 2019 - dl.acm.org
Code smells can compromise software quality in the long term by inducing technical debt.
For this reason, many approaches aimed at identifying these design flaws have been …

Deep learning based code smell detection

H Liu, J Jin, Z Xu, Y Zou, Y Bu… - IEEE transactions on …, 2019 - ieeexplore.ieee.org
Code smells are structures in the source code that suggest the possibility of refactorings.
Consequently, developers may identify refactoring opportunities by detecting code smells …

[HTML][HTML] Automatic detection of Long Method and God Class code smells through neural source code embeddings

A Kovačević, J Slivka, D Vidaković, KG Grujić… - Expert Systems with …, 2022 - Elsevier
Code smells are structures in code that often harm its quality. Manually detecting code
smells is challenging, so researchers proposed many automatic detectors. Traditional code …

Detecting code smells using deep learning

AK Das, S Yadav, S Dhal - TENCON 2019-2019 IEEE Region …, 2019 - ieeexplore.ieee.org
A smell in software refers to a symptom introduced in software artifacts such as architecture,
design or code. A code smell can potentially cause deeper and serious problems, while …

Code-smell detection as a bilevel problem

D Sahin, M Kessentini, S Bechikh, K Deb - ACM Transactions on …, 2014 - dl.acm.org
Code smells represent design situations that can affect the maintenance and evolution of
software. They make the system difficult to evolve. Code smells are detected, in general …

A large empirical assessment of the role of data balancing in machine-learning-based code smell detection

F Pecorelli, D Di Nucci, C De Roover… - Journal of Systems and …, 2020 - Elsevier
Code smells can compromise software quality in the long term by inducing technical debt.
For this reason, many approaches aimed at identifying these design flaws have been …