Abstract
Effective bug classification and assignment to relevant developers improves the efficiency of software management. However, textually dependent approaches produce inconsistent results on varying datasets, while approaches that depend upon multi-source data can produce dataset conflicts and inaccuracy. Accordingly, we introduce a model based on Self-Paced Association augmentation and Node embedding (SPAN), which uses an effective combination of textually dependent and independent bug categorization to produce consistent results, followed by a bug assignment mechanism to prevent conflicts. To this end, we present a novel unified classifier and assignment model that exploits the connections between nodes in the Software Bug Report Network (SBRNet) to identify the target features. The model is capable of accurately categorizing bugs in a self-paced manner with association augmentation. Finally, we present an approach that assigns the most appropriate developer for bug resolution through SBRNet node information embedding. Our deep two-step self-paced solution is capable of categorizing software bugs with improved accuracy, while still utilizing fewer features. Results reveal that our model is more effective (up to 98% classification accuracy and 96% for bug assignment) when compared to its counterparts.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
