A Survey on Bug Triage Using Data Reduction Technique

Abstract

Most of the software companies needs to deal with software bug in every day. Software companies spend most if their cost in dealing with software bugs. The process of fixing bug is bug triage, which aims to assign a expert developer to a new bug. To reduce the time and cost in manual work, we apply text classification technique to conduct automatic bug triage. In proposed system we apply data reduction techniques on bug data set to improve the scale and quality of bug data. We use instance selection and feature selection simultaneously to reduce the scales on bug dimension and word dimension and improve the accuracy of bug triage. In this paper, we investigate the use of five term selection methods on the accuracy of bug assignment. In addition, we re-balance the load between developers based on their experience.