An Empirical Study on the Short-Term Self-Admitted Technical Debt

Self-Admitted Technical Debt (SATD) is commonly used to refer to suboptimal implementations in software development. Due to constraints such as limited development resources, many developers are unable to repair SATD promptly after introducing it. This challenge has led to research on SATD prioritization, aiming to help developers identify which kind of SATD should be repaired first. However, existing studies lack a standardized definition of prioritization and a systematic study on these SATD. In this paper, we consider a newly-introduced SATD that are repaired before the the next release version to have the highest repair priority, referring to it as short-term SATD. From over 6,500 historical release versions of Open-Source software (OSS), we identified 5,234 instances of short-term SATD and, for the first time, described the distribution of SATD across surviving versions. For all extracted SATD, we characterize them from three dimensions and highlight the differences between short-term SATD and other SATD in these features. Finally, we trained six popular machine learning and deep learning models to explore their performance in identifying short-term SATD and revealed the driving effects of key features on prediction results. These comprehensive research findings provide developers with a transparent basis for SATD repairing.