Code smells are seen as a 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 mitigating the problem of smells-infected code.
This paper presents the results of a validation experiment for the Crowdsmelling approach proposed earlier. The latter is 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.
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).
The results suggest that Crowdsmelling is a feasible approach for the detection of code smells. Further validation experiments based on dynamic learning are required to comprehensive coverage of code smells to increase external validity.