A Bug Triage Technique Using Developer-Based Feature Selection and CNN-LSTM Algorithm

With an increase in the use of software, incidence bugs and resulting maintenance costs also increase. In open source projects, developer reassignment accounts for approximately 50%. Software can be reduced if appropriate developers are recommended to resolve bugs. this study, features extracted by applying feature selection each developer. These entered into CNN-LSTM algorithm learn model recommend developers. To compare performance proposed model, projects (Google Chrome, Mozilla Core, Firefox) were used method with a baseline recommendation. paper, showed 54% F-measure 52% accuracy projects. The has improved about 13% more effective improvement than DeepTriage. It was discovered that better.