Crowdsmelling: The use of collective knowledge in code smells detection

TL;DR

This paper introduces crowdsmelling, a machine learning-based approach that leverages collective developer knowledge to improve code smell detection, showing promising results especially for certain smells like God Class and Long Method.

Contribution

It presents a novel crowd-based calibration method for code smell detection algorithms, reducing subjectivity and enhancing detection accuracy through collective input.

Findings

High detection performance for God Class (ROC=0.896)

Good results for Long Method detection (ROC=0.870)

Lower performance for Feature Envy (ROC=0.570)

Abstract

Code smells are seen as major source of technical debt and, as such, should be detected and removed. However, researchers argue that the subjectiveness of the code smells detection process is a major hindrance to mitigate the problem of smells-infected code. We proposed the crowdsmelling approach based on supervised machine learning techniques, where the wisdom of the crowd (of software developers) is used to collectively calibrate code smells detection algorithms, thereby lessening the subjectivity issue. This paper presents the results of a validation experiment for the crowdsmelling approach. In the context of three consecutive years of a Software Engineering course, a total "crowd" of around a hundred teams, with an average of three members each, classified the presence of 3 code smells (Long Method, God Class, and Feature Envy) in Java source code. These classifications were the basis of the oracles used for training six machine learning algorithms. Over one hundred models were generated and evaluated to determine which machine learning algorithms had the best performance in detecting each of the aforementioned code smells. Good performances were obtained for God Class detection (ROC=0.896 for Naive Bayes) and Long Method detection (ROC=0.870 for AdaBoostM1), but much lower for Feature Envy (ROC=0.570 for Random Forrest). Obtained results suggest that crowdsmelling is a feasible approach for the detection of code smells, but further validation experiments are required to cover more code smells and to increase external validity.