Software Defect Prediction via Attention-Based Recurrent Neural Network

• Published in: Scientific programming Vol. 2019; no. 2019; pp. 1 - 14
• Main Authors: Yang, Kang, Yu, Huiqun, Diao, Xuyang, Fan, Guisheng, Chen, Liqiong
• Format: Journal Article
• Language: English
• Published: Cairo, Egypt Hindawi Publishing Corporation 01.01.2019; Hindawi; John Wiley & Sons, Inc
• Subjects: Artificial intelligence; Classification; Data mining; Defects; Dictionaries; Identification methods; Machine learning; Mapping; Network reliability; Neural networks; Prediction models; Recurrent neural networks; Semantics; Software engineering; Software reliability; Source code
• ISSN: 1058-9244; 1875-919X
• DOI: 10.1155/2019/6230953

In order to improve software reliability, software defect prediction is applied to the process of software maintenance to identify potential bugs. Traditional methods of software defect prediction mainly focus on designing static code metrics, which are input into machine learning classifiers to predict defect probabilities of the code. However, the characteristics of these artificial metrics do not contain the syntactic structures and semantic information of programs. Such information is more significant than manual metrics and can provide a more accurate predictive model. In this paper, we propose a framework called defect prediction via attention-based recurrent neural network (DP-ARNN). More specifically, DP-ARNN first parses abstract syntax trees (ASTs) of programs and extracts them as vectors. Then it encodes vectors which are used as inputs of DP-ARNN by dictionary mapping and word embedding. After that, it can automatically learn syntactic and semantic features. Furthermore, it employs the attention mechanism to further generate significant features for accurate defect prediction. To validate our method, we choose seven open-source Java projects in Apache, using F1-measure and area under the curve (AUC) as evaluation criteria. The experimental results show that, in average, DP-ARNN improves the F1-measure by 14% and AUC by 7% compared with the state-of-the-art methods, respectively.