CaPBug-A Framework for Automatic Bug Categorization and Prioritization Using NLP and Machine Learning Algorithms

Bug reports facilitate software development teams in improving the quality of software. These include significant information related to problems encountered within a software, possible enhancement suggestions, and other potential issues. are typically complex too detailed; hence lot resources required analyze process them manually. Moreover, it leads delays resolution high priority bugs. Accurate timely processing bug based on their category plays role maintenance. Therefore, an automated categorization prioritization is needed address aforementioned Automated have been explored recently by many researchers; however, limited progress has made this regard. In research, we present novel framework, titled CaPBug, for reports. The framework implemented using Natural Language Processing (NLP) supervised machine learning algorithms. A baseline corpus built with six categories five levels analyzing more than 2000 Mozilla Eclipse repository. Four classification algorithms i.e., Naive Bayes, Random Forest, Decision Tree, Logistic Regression used categorize prioritize We demonstrate that CaPBug achieved accuracy 88.78% Forest classifier textual feature predicting category. Similarly, 90.43% was Synthetic Minority Over-Sampling Technique (SMOTE) applied class imbalance issue classes.