Move method refactoring recommendation based on deep learning and LLM-generated information

• Published in: Information sciences Vol. 697; p. 121753
• Main Authors: Zhang, Yang, Li, Yanlei, Meredith, Grant, Zheng, Kun, Li, Xiaobin
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.04.2025
• Subjects: Deep learning; Large language models; Move method; Prompt engineering; Refactoring recommendation; Move method; Deep learning; Large language models; Prompt engineering; Refactoring recommendation
• ISSN: 0020-0255
• DOI: 10.1016/j.ins.2024.121753

Move method refactoring is a prevalent technique typically applied when a method relies more on members of other classes than on its original class. Existing approaches for move method refactoring recommendations have improved accuracy based on deep learning. However, it is challenging to capture the deep semantics behind the code and the true intention of the developer. Furthermore, the accuracy of move method refactoring needs to be improved. To alleviate these problems, this paper proposes MoveRec, a move method refactoring recommendation based on deep learning and LLM-generated information. To generate the dataset, MoveRec selects 58 real-world projects from which it extracts metric, textual, and semantic features. Metric features are derived using static analysis tools. Textual features are generated with LLM to obtain code summaries, and the pre-trained model is used to produce word vectors. Semantic features are obtained by calculating the similarity between the original and target classes. Finally, we construct a dataset with 12,475 samples. A deep learning model CNN-LSTM-GRU is designed for refactoring recommendations. We evaluate MoveRec on this dataset and experimental results show that the average F1 is 74%. Compared to existing methods including PathMove, JDeodorant, JMove, and RMove, MoveRec improves F1 ranging from 9.4% to 53.4%, demonstrating its effectiveness.