Enhanced Bug Report Classification using XGBoost and Transformer-based NLP Models

P Vamsi; Dr. I. Nasrulla

Enhanced Bug Report Classification using XGBoost and Transformer-based NLP Models

Authors: P Vamsi, Dr. I. Nasrulla

Unique Paper ID: 175786
Volume: 11
Issue: 11
PageNo: 5022-5025

Keywords: No Keywords Found

Abstract:
In software development, maintaining software systems has garnered attention due to the critical task of fixing defects identified during testing through bug reports (BRs). These BRs contain key details such as description, status, priority, and severity of bugs. The challenge lies in analyzing these growing numbers of BRs, which can be time-consuming and labor-intensive when done manually. Automation offers a promising solution. While much research focuses on automating tasks like predicting bug severity or priority, little attention is given to classifying the nature of the bugs. This paper proposes a new prediction model using natural language processing (NLP) and machine learning to automate this process. Simulated on publicly available datasets, the model demonstrated improved accuracy in predicting multi-class bug categories. Bug reports are essential for identifying and resolving issues in software systems. However, manual analysis of these reports is often time-consuming, error-prone, and inefficient due to the increasing volume and complexity of data. To address these challenges, this project proposes a nature-based prediction model that leverages ensemble machine learning techniques, particularly XGBoost, in combination with transformer-based Natural Language Processing (NLP) models. The approach automates the classification of bug reports into six distinct categories: Client, General, Hyades, Releng, Xtext, and CDT-core. Utilizing publicly available datasets from Eclipse and Mozilla, the model demonstrates superior performance, with XGBoost achieving an accuracy of 92%, outperforming other traditional models like SVM, Random Forest, and Logistic Regression. This system enhances software maintenance by improving classification accuracy, reducing manual effort, and expediting the bug resolution process.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 11
Issue: 11
PageNo: 5022-5025

Enhanced Bug Report Classification using XGBoost and Transformer-based NLP Models

Available:https://ijirt.org/Article?manuscript=175786

18 Apr, 2025

A HYBRID DEEP LEARNING APPROACH FOR EARLY PARKINSON’S DETECTION FROM HANDWRITING

14 Apr, 2025

Pain Hybrid Model For Pain Recosnitionusins CNN+BL-LSTM+BL-SRU

14 Apr, 2025

Deep Learning Approach to Identify Skin Cancer Diagnosis Using Decoding Predefined

14 Apr, 2025

A Feature-Turned XGBoost Model For Real Time SOC Prediction

14 Apr, 2025

Legal Text Similarity Analysis Using Deep Learning Based Model With Enhanced Feature Extraction

14 Apr, 2025

A Multi-Client Secure Cloud Framework with Enhanced Storage Efficiency and Latency Reduction

14 Apr, 2025

Age and Gender Detection Using Python and opencv

14 Apr, 2025

Scalable and Efficient Food Quality Monitoring Using CNN for Supply Chain Optimization

14 Apr, 2025

THE HYBRID APPROACH USING TF-IDF,XG BOOST AND LIGHT GBM FOR LOG EVENT DETECTION

14 Apr, 2025

Federated Learning with XGBoost and LSTM for Electric Vehicle Energy Demand Prediction

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now

Latest Publication

Recent Conferences

NCSEM 2024

National Conference on Sustainable Engineering and Management - 2024 Last Date: 15th March 2024

Submit inquiry