Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers

Abstract

Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process-especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough.

On the use of Machine Learning and Deep Learning for Text Similarity and Categorization and its Application to Troubleshooting Automation

“…Despite the purpose of that categorization, they are all based on the principle of text classification. For example, Zaidi et al [6] propose a CNN framework to assign a bug classified from their textual information (e.g., summary and description) to a specific developer, which, in essence, is the same as categorizing a problem and assigning it to someone or something related to that category. To compare their performances, they test the framework using word embeddings, such as Word2Vec, GloVe, and ELMo.…”

“…In the final list of selected papers, the ones in the bug-triage section are well related to this research, especially Zaidi et al [6] and Lee et al [4]. Bug as a software problem can be considered an issue.…”

“…Directly approaches TA -Classifying the issue [2,3,4,5,6,16,21,22,23,24,25,26,28,30,31,33,36,37,38,39,40,41,42,43] -Dealing with imbalanced data [15] Indirectly approaches TA -Analyzing historical interactions data [17,20,34] -Identifying double-meaning terms [29,32,35] -Identifying languages [18,27] -Receiving feedback…”

“…For example, we can use models for text similarity recognition and text categorization or classification to learn from text [1]. Being able to identify text similarity and its categorization allows us to solve problems such as helping answer questions in community-based websites [2], predict author gender based on the text they wrote [3], and tasks related to bug-triage [4,5,6,7] to automate the resolution of issues.…”

A Graph Convolution Network-Based Bug Triage System to Learn Heterogeneous Graph Representation of Bug Reports

“…Mani et al [3] proposed an attention-based bidirectional recurrent neural network that also used word2vec embedding. Zaidi et al [4] used different context-aware and contextinsensitive techniques for word-representation with a CNN model. They produced promising results compared to previous methods.…”