A Text Mining Framework for Analyzing Change Impact and Maintenance Effort of Software Bug Reports

Abstract

Software practitioners often strive to achieve a “bug-free” software, though, it is a myth. Software Bug Categorization (SBC) models, which assigns levels (viz. “low”, “moderate” or “high”) to a software bug aid effective bug management. They assist in allocation of proper maintenance resources for bug elimination to improve software quality. This study proposes the development of SBC models that allocate levels on the basis of three software bug aspects i.e., maintenance effort required to correct a bug, its change impact and the combined effect of both of these. In order to develop SBC models, we use text mining approach, which extracts relevant features from bug descriptions and relates these features with different software bug levels. The results of the study indicate that the categorization of software bugs in accordance with maintenance effort and change impact is possible. Furthermore, the combined approach SBC models were also found to be effective.

Software Sentiment Analysis using Deep-learning Approach with Word-Embedding Techniques

“…After evaluation, it was found that the performance of the combined SBC model showed higher accuracy than the ME or CI SBC models. They also found that the accuracy of the "high" category was superior to that of the other categories [7]. R Malhotra et al have worked to find out if resampling methods applied to software defect data improve performance.…”