Improving Blocking Bug Pair Prediction via Hybrid Deep Learning
Zhihua Chen, Xiaolin Ju, Yiheng Shen, Xiang Chen · 2021 IEEE 21st International Conference on Software Quality, Reliability and Security Companion (QRS-C) · 2021
Blocking bug pair (BBP) is a critical relationship between bugs that indicate one bug prevent the other bug from being fixed in time and cost more effort to repair itself in software maintenance. We propose a novel blocking bug pair prediction approach based on the combination of Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neu-ral Network (CNN). Specifically, our approach first extracts summaries and descriptions from bug reports to construct two classifiers, respectively. Second, our approach combines two classifiers into a hybrid model to predict the blocking relationship of each blocking bug pair. Finally, our approach generates a report of identified blocking bugs for developers. We conduct an empirical study on five large-scale open-source projects. The final experimental results show that our approach can achieve better performance than the recent state-of-the-art baseline techniques.