Object Oriented Metrics Based Empirical Model for Predicting “Code Smells” in Open Source Software

• Published in: Journal of the Institution of Engineers (India). Series B, Electrical Engineering, Electronics and telecommunication engineering, Computer engineering Vol. 104; no. 1; pp. 241 - 257
• Main Authors: Kaur, Sharanpreet, Singh, Satwinder
• Format: Journal Article
• Language: English
• Published: New Delhi Springer India 01.02.2023; Springer Nature B.V
• Subjects: Communications Engineering; Engineering; Fault detection; Internal layout; Networks; Open source software; Original Contribution; Software; Source code; Refactoring; Code Smells; Faults; Area under Curve (ROC)
• ISSN: 2250-2106; 2250-2114
• DOI: 10.1007/s40031-022-00833-4

Refactoring is a technique which involves the change in internal layout of software system while keeping external features same as before. It aims at identification of smelly areas in code in order to apply patch. The presence of these smelly areas in code is also called “Code Smells” generally known as “Bad Smells.” Under the present study, the statistical relationship between software metrics, code smells and faults is investigated in open source systems. Eight versions of two open source projects – Eclipse and Tomcat are investigated in order to identify the effect on classes subject to code smells and faults than other classes. It was observed that in almost all releases of Tomcat, a good perceptiveness was revealed by area under ROC curve. While an excellent perceptiveness was collected by class level code smells for Eclipse, whereas a fair to good discrimination is generated by method level code smells by area under ROC curve. The results obtained from the study showed that software metrics model for smelly classes is helpful in predicting classes.