Follow-up maintenance reports are important and tedious work. Bug repository is usually used to store maintenance reports which could be: fault repair, Functionality addition or modification, or environmental adaptation. Labeling these maintenance reports can reduce the time and effort of handling them. We proposed an approach that classifies maintenance reports into different categories. We applied a machine learning pipeline to achieve classification. We reached up to 78% precision, 83% recall, and 79%F1-score. Adopting such an approach can speedup handling maintenance reports and increase user satisfaction.
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL