2020/12/10 by Jiaxi Xu, Fei Wang, Jun Ai · 1 citation
Computer Science · #Abstract syntax #Artificial intelligence #Computer science #Data mining #Database #Graph #Machine learning #Programming language #Semantics (computer science) #Software #Software Engineering Research #Software Reliability and Analysis Research #Software System Performance and Reliability #Software bug #Software development #Software quality #Static program analysis #Syntax #Theoretical computer science #Workflow
paper · doi:10.1109/tr.2020.3040191
openalex publication_date 2020/12/10 · crossref created 2020/12/10 · crossref issued 2021/06/01 · crossref published 2021/06/01 · crossref published-print 2021/06/01 · crossref deposited 2021/10/26 · openalex created_date 2025/10/10 · crossref indexed 2026/08/04 · openalex updated_date 2026/08/04
To optimize the process of software testing and to improve software quality and reliability, many attempts have been made to develop more effective methods for predicting software defects. Previous work on defect prediction has used machine learning and artificial software metrics. Unfortunately, artificial metrics are unable to represent the features of syntactic, semantic, and context information of defective modules. In this article, therefore, we propose a practical approach for identifying software defect patterns via the combination of semantics and context information using abstract syntax tree representation learning. Graph neural networks are also leveraged to capture the latent defect information of defective subtrees, which are pruned based on a fix-inducing change. To validate the proposed approach for predicting defects, we define mining rules based on the GitHub workflow and collect 6052 defects from 307 projects. The experiments indicate that the proposed approach performs better than the state-of-the-art approach and five traditional machine learning baselines. An ablation study shows that the information about code concepts leads to a significant increase in accuracy.