Machine Learning Techniques for Code Smells Detection: A Systematic Mapping Study

Abstract

Code smells or bad smells are an accepted approach to identify design flaws in the source code. Although it has been explored by researchers, the interpretation of programmers is rather subjective. One way to deal with this subjectivity is to use machine learning techniques. This paper provides the reader with an overview of machine learning techniques and code smells found in the literature, aiming at determining which methods and practices are used when applying machine learning for code smells identification and which machine learning techniques have been used for code smells identification. A mapping study was used to identify the techniques used for each smell. We found that the Bloaters was the main kind of smell studied, addressed by 35% of the papers. The most commonly used technique was Genetic Algorithms (GA), used by 22.22% of the papers. Regarding the smells addressed by each technique, there was a high level of redundancy, in a way that the smells are covered by a wide range of algorithms. Nevertheless, Feature Envy stood out, being targeted by 63% of the techniques. When it comes to performance, the best average was provided by Decision Tree, followed by Random Forest, Semi-supervised and Support Vector Machine Classifier techniques. 5 out of the 25 analyzed smells were not handled by any machine learning techniques. Most of them focus on several code smells and in general there is no outperforming technique, except for a few specific smells. We also found a lack of comparable results due to the heterogeneity of the data sources and of the provided results. We recommend the pursuit of further empirical studies to assess the performance of these techniques in a standardized dataset to improve the comparison reliability and replicability.

Severity classification of software code smells using machine learning techniques: A comparative study

“…RBF neural network Regression RBF 35 is fast in learning and it produces exact interpolation. RBF depends on the theory of function approximation by using Gaussian Function.…”

Improving Accuracy of Code Smells Detection with Data Balancing Techniques

“…Detection rules are approaches used to detect code smells through a combination of different software metrics with predefined threshold values. Most of the current detectors need the specification of thresholds that allow them to distinguish smelly and non-smelly code [27]. Many approaches have been presented by the authors for uncovering the smells from the software systems.…”

Software smell detection techniques: A systematic literature review

“…ML-based smell detection techniques are reviewed in other studies. 18,19 In previous works, 18,19 Azeem et al and Caram et al explored 15 and 19 research articles, respectively. In both SLRs, a deep investigation of smell detection techniques is provided.…”

“…Moreover, they studied the impact of the training procedures on the code smell detection performance. In addition to previous works 18,19 and the strategy of previous studies, 18,19 our SLR includes smell detection techniques that are based on ML and other paradigms. Table 1 summarizes the existing SLR studies on the smell detection techniques and tools.…”