Machine Learning-Based Test Smell Detection
This work addresses the issue of limited performance in automated test smell detection for software developers, but it appears incremental as it builds on existing heuristic methods by applying machine learning.
The authors tackled the problem of detecting test smells, which are sub-optimal design choices in test code that harm maintainability, by proposing a machine learning-based approach to detect four test smells, with plans to develop the largest manually-validated dataset and compare against state-of-the-art heuristic techniques.
Context: Test smells are symptoms of sub-optimal design choices adopted when developing test cases. Previous studies have proved their harmfulness for test code maintainability and effectiveness. Therefore, researchers have been proposing automated, heuristic-based techniques to detect them. However, the performance of such detectors is still limited and dependent on thresholds to be tuned. Objective: We propose the design and experimentation of a novel test smell detection approach based on machine learning to detect four test smells. Method: We plan to develop the largest dataset of manually-validated test smells. This dataset will be leveraged to train six machine learners and assess their capabilities in within- and cross-project scenarios. Finally, we plan to compare our approach with state-of-the-art heuristic-based techniques.