Automatic detection of Long Method and God Class code smells through neural source code embeddings

Code smells are structures in code that often harm its quality. Manually detecting code smells is challenging, so researchers proposed many automatic detectors. Traditional code smell detectors employ metric-based heuristics, but researchers have recently adopted a Machine-Learning (ML) based approach. This paper compares the performance of multiple ML-based code smell detection models against multiple metric-based heuristics for detection of God Class and Long Method code smells. We assess the effectiveness of different source code representations for ML: we evaluate the effectiveness of traditionally used code metrics against code embeddings (code2vec, code2seq, and CuBERT). This study is the first to evaluate the effectiveness of pre-trained neural source code embeddings for code smell detection to the best of our knowledge. This approach helped us leverage the power of transfer learning - our study is the first to explore whether the knowledge mined from code understanding models can be transferred to code smell detection. A secondary contribution of our research is the systematic evaluation of the effectiveness of code smell detection approaches on the same large-scale, manually labeled MLCQ dataset. Almost every study that proposes a detection approach tests this approach on the dataset unique for the study. Consequently, we cannot directly compare the reported performances to derive the bestperforming approach.

Automated summary

This paper compares the performance of machine learning-based and metric-based code smell detection methods, and evaluates the effectiveness of different source code representations. The study also explores the transferability of knowledge mined from code understanding models to code smell detection and provides a systematic evaluation of code smell detection approaches.