Deep Learning Models for Software Defect Classification

With the increasing reliance on automatic software-based applications, it is critical to automate software defect classification and assure software dependability. This article proposes an expert-based automatic software flaw classification system. Defect report categorization is the process of categorizing defects into predefined groups. Many machine learning (ML) algorithms have recently been presented to categorize defect in various classes. This research proposes a classification model based on the Long Short Term Memory (LSTM) network and Convolution Neural Network (CNN) that uses these deep learning (DL) models to categorize defect reports by generating new word embedding from the defect reports. In terms of recall, accuracy and precision, the results are compared to pre-trained word embedding using Google's word2vec. According to the experimental results, LSTM beats the other models utilized in the study. On the redmine dataset, LSTM achieves a maximum accuracy of 70%.