DOI

  • Dario Di Nucci
  • Fabio Palomba
  • Damian Tamburri
  • Alexander Serebrenik
  • Andrea De Lucia
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 tools have been proposed.
However, the literature shows that the results of these tools can be subjective and are intrinsically tied to the nature and approach of the detection.
In a recent work the use of Machine-Learning (ML) techniques for code smell detection has been proposed, possibly solving the issue of tool subjectivity giving to a learner the ability to discern between smelly and non-smelly source code elements.
While this work opened a new perspective for code smell detection, it only considered the case where instances affected by a single type smell are contained in each dataset used to train and test the machine learners. In this work we replicate the study with a different dataset configuration containing instances of more than one type of smell. The results reveal that with this configuration the machine learning techniques reveal critical limitations in the state of the art which deserve further research.
Original languageEnglish
Title of host publicationin Proceedings of the 25th International Conference on Software Analysis, Evolution and Reengineering
PublisherIEEE
Pages612-621
Number of pages10
ISBN (Electronic)978-1-5386-4969-5
ISBN (Print)978-1-5386-4970-1
DOIs
StatePublished - 20 Mar 2018
Event25th International Conference on Software Analysis, Evolution and Reengineering - Campobasso, Italy
Duration: 20 Mar 201823 Mar 2018
Conference number: 25
http://saner.unimol.it

Conference

Conference25th International Conference on Software Analysis, Evolution and Reengineering
Abbreviated titleSANER
CountryItaly
CityCampobasso
Period20/03/1823/03/18
Internet address

    Research areas

  • Code Smells, Machine Learning, Empirical Studies, Replication Study

ID: 36483197