Enhancing bug localization with bug report decomposition and code hierarchical network

作者：

Highlights：

• A graph-based neural model is proposed to handle complex, large-scale software systems for the automatic bug localization task.

• A decomposition strategy is designed for bug reports, with advantages for bug-related information extraction.

• Code-NoN is the first hierarchical graph data structure for representing programs in a more complete view.

摘要

•A graph-based neural model is proposed to handle complex, large-scale software systems for the automatic bug localization task.•A decomposition strategy is designed for bug reports, with advantages for bug-related information extraction.•Code-NoN is the first hierarchical graph data structure for representing programs in a more complete view.

论文关键词：Software mining,Bug localization,Bug report,Program behavior,Hierarchical network,Network of networks

论文评审过程：Received 18 November 2021, Revised 1 April 2022, Accepted 1 April 2022, Available online 27 April 2022, Version of Record 11 May 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108741