A Survey of Learning-based Method Name Prediction

The choice of method names significantly influences code comprehension and maintenance, posing a considerable challenge, especially for novice developers. Automating the prediction of appropriate method names based on the method code body has emerged as a promising approach to address this challenge. In recent years, numerous machine/deep learning (ML/DL)-based method name prediction (MNP) techniques have been proposed. However, a systematic review of these techniques is currently lacking, hindering future researchers from understanding the research status, development trends, challenges, and opportunities in this field. To fill this gap, in this paper, we conduct a systematic literature review on learning-based MNP studies. Specifically, we first perform a thorough review of the literature concerning publication venue, publication year, and contribution types. This analysis enables us to discern trends in studies related to MNP. Second, we depict the general workflow of learning-based MNP techniques, which involves three consecutive subprocesses: context extraction, context preprocessing, and context-based prediction. Subsequently, we investigate contemporary techniques/solutions applied in the three subprocesses. Third, we scrutinize the widely used experimental databases, evaluation metrics, and replication packages utilized in MNP studies. Moreover, we summarize existing empirical studies on MNP to facilitate a quick understanding of their focus and findings for subsequent researchers. Finally, based on a systematic review and summary of existing work, we outline several open challenges and opportunities in MNP that remain to be addressed in future work.