ADPTriage: Approximate Dynamic Programming for Bug Triage

Jahanshahi, Hadi; Cevik, Mucahit; Mousavi, Kianoush; Başar, Ayşe

doi:10.1109/tse.2023.3307243

Cited by 1 publication

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the continuous development of machine learning technology, some researchers utilized traditional machine-learning and deep-learning algorithms to solve the developer assignment task [14,[18][19][20][21][22][36][37][38][39]. Jonsson et al [19] proposed a defect assignment method based on ensemble learner, using TF-IDF technology to extract features from the title information and description information of defect reports and combining Naive Bayes, Support Vector Machines, KNN, and Decision Tree classifiers to create a stacked generalization classifier for improving the prediction accuracy of automatic developer assignment.…”

Section: Machine Learning-based Approachmentioning

confidence: 99%

Developer Assignment Method for Software Defects Based on Related Issue Prediction

Liu,

Zhang,

Liu

et al. 2024

Mathematics

View full text Add to dashboard Cite

The open-source software platform hosts a large number of software defects, and the task of relying on administrators to manually assign developers is often time consuming. Thus, it is crucial to determine how to assign software defects to appropriate developers. This paper presents DARIP, a method for assigning developers to address software defects. First, the correlation between software defects and issues is considered, predicting related issues for each defect and comprehensively calculating the textual characteristics of the defect using the BERT model. Second, a heterogeneous collaborative network is constructed based on the three development behaviors of developers: reporting, commenting, and fixing. The meta-paths are defined based on the four collaborative relationships between developers: report–comment, report–fix, comment–comment, and comment–fix. The graph-embedding algorithm metapath2vec extracts developer characteristics from the heterogeneous collaborative network. Then, a classifier based on a deep learning model calculates the probability assigned to each developer category. Finally, the assignment list is obtained according to the probability ranking. Experiments on a dataset of 20,280 defects from 9 popular projects show that the DARIP method improves the average of the Recall@5, the Recall@10, and the MRR by 31.13%, 21.40%, and 25.45%, respectively, compared to the state-of-the-art method.

show abstract