期刊名称:International Journal of Software Engineering & Applications (IJSEA)
印刷版ISSN:0976-2221
电子版ISSN:0975-9018
出版年度:2018
卷号:9
期号:2
出版社:Academy & Industry Research Collaboration Center (AIRCC)
摘要:Most bug assignment approaches utilize text classification and information retrieval techniques. Theseapproaches use the textual contents of bug reports to build recommendation models. The textual contents ofbug reports are usually of high dimension and noisy source of information. These approaches suffer fromlow accuracy and high computational needs. In this paper, we investigate whether using categorical fieldsof bug reports, such as component to which the bug belongs, are appropriate to represent bug reportsinstead of textual description. We build a classification model by utilizing the categorical features, as arepresentation, for the bug report. The experimental evaluation is conducted using three projects namelyNetBeans, Freedesktop, and Firefox. We compared this approach with two machine learning based bugassignment approaches. The evaluation shows that using the textual contents of bug reports is important. Inaddition, it shows that the categorical features can improve the classification accuracy.