Data Balancing Improves Self-Admitted Technical Debt Detection

TL;DR

This study investigates how different data balancing techniques affect the accuracy of Self-Admitted Technical Debt detection, revealing that classical machine learning models with balancing methods outperform deep learning in within-project scenarios.

Contribution

It provides an empirical comparison of multiple balancing techniques and models for SATD detection, including a new benchmark and a web-based prediction tool.

Findings

Data balancing improves SATD detection performance.

Classical ML models outperform deep learning in within-project detection.

SMOTE and ensemble methods are effective balancing techniques.

Abstract

A high imbalance exists between technical debt and non-technical debt source code comments. Such imbalance affects Self-Admitted Technical Debt (SATD) detection performance, and existing literature lacks empirical evidence on the choice of balancing technique. In this work, we evaluate the impact of multiple balancing techniques, including Data level, Classifier level, and Hybrid, for SATD detection in Within-Project and Cross-Project setup. Our results show that the Data level balancing technique SMOTE or Classifier level Ensemble approaches Random Forest or XGBoost are reasonable choices depending on whether the goal is to maximize Precision, Recall, F1, or AUC-ROC. We compared our best-performing model with the previous SATD detection benchmark (cost-sensitive Convolution Neural Network). Interestingly the top-performing XGBoost with SMOTE sampling improved the Within-project F1 score by 10% but fell short in Cross-Project set up by 9%. This supports the higher generalization capability of deep learning in Cross-Project SATD detection, yet while working within individual projects, classical machine learning algorithms can deliver better performance. We also evaluate and quantify the impact of duplicate source code comments in SATD detection performance. Finally, we employ SHAP and discuss the interpreted SATD features. We have included the replication package and shared a web-based SATD prediction tool with the balancing techniques in this study.