Method-Based and BERT-Based Bug Prediction in Open Source Software: A Comparative Study
Loading...
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh
Abstract
Bug prediction is essential for maintaining software quality, but manual processes
are inefficient and error-prone. This study compares traditional method-level bug
prediction techniques with modern NLP approaches, focusing on pre-trained lan
guage models like BERT. Using a GitHub issues dataset, we analyze the effective
ness, challenges, and practical implications of both methodologies. Our findings
show that while method-level approaches remain robust when historical data is
available, BERT-based models provide competitive performance and unique ad
vantages, particularly in scenarios lacking detailed code history
Description
Supervised by
Mr. Nazmul Hossain,
Assistant Professor,
Department of Computer Science and Engineering (CSE)
Islamic University of Technology (IUT)
Board Bazar, Gazipur, Bangladesh
This thesis is submitted in partial fulfillment of the requirement for the degree of Bachelor of Science in Computer Science and Engineering, 2025