Imagen de Portada

AN ENSEMBLE MACHINE LEARNING APPROACH FOR BUG REPORT PREDICTION INSPIRED BY NATURE-BASED MODELS

Guardado en:
Publicado en:International Journal of Communication Networks and Information Security vol. 17, no. 3 (2025), p. 203-209
Autor principal: Nagagopiraju, V
Otros Autores: Navyasre, Pothuguntla, Varshitha, Tamma, Kumar, Anisetti Praveen, Manikanta, Bethamcherla
Publicado:
Kohat University of Science and Technology (KUST)
Materias:
Software quality
Machine learning
Accuracy
Metadata
Datasets
Software development
Configuration management
Prediction models
Optimization techniques
Genetic algorithms
Classification
Support vector machines
Debugging
Natural language processing
Development systems
Automation
Defects
Software testing
Software development tools
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:In software development systems, the maintenance process of software systems attracted the attention of researchers due to its importance in fixing the defects discovered in the software testing by using bug reports (BRs) which include detailed information like descriptions, status, reporter, assignee, priority, and severity of the bug and other information. The main problem in this process is how to analyze these BRs to discover all defects in the system, which is a tedious and timeconsuming task if done manually because the number of BRs increases dramatically. Thus, the automated solution is the best. Most of the current research focuses on automating this process from different aspects, such as detecting the severity or priority of the bug. However, they did not consider the nature of the bug, which is a multi-class classification problem. This paper solves this problem by proposing a new prediction model to analyze BRs and predict the nature of the bug. The proposed model constructs an ensemble machine learning algorithm using natural language processing (NLP) and machine learning techniques. We simulate the proposed model by using a publicly available dataset for two online software bug repositories (Mozilla and Eclipse), which includes six classes: Program Anomaly, GUI, Network or Security, Configuration, Performance, and Test-Code. The simulation results show that the proposed model can achieve better accuracy than most existing models, namely, 90.42% without text augmentation and 96.72% with text augmentation.
ISSN:2073-607X
2076-0930
Fuente:Science Database