GitHub Bug Classification Using Pipeline Approach in Machine Learning

GitHub bug classification refers to the process of automatically categorizing bug reports or issues on GitHub into predefined categories based on their text content. This process helps to improve the efficiency of software development teams by reducing the time spent on manual issue triage. By using machine learning techniques such as Naive Bayes, Decision Trees, and Logistic Regression, a model can be trained on a dataset of past issues and then used to classify new issues as they are submitted. This study aims to build a machine-learning model for GitHub bug classification using a pipeline approach and evaluate its accuracy, precision, and recall performance.The study also includes a comprehensive literature review of bug tracking and classification techniques, existing systems and approaches, and evaluation metrics for performance measures. The research design and strategy, data collection and sources, and ethical considerations are also discussed in detail.The practice of automatically classifying bug reports or issues on GitHub into specified categories based on their text content is called GitHub bug categorization. By cutting down on the time needed for manual problem triage, this technique increases the effectiveness of software development teams.