Construção de um classificador automático de severidade de bugs para sistemas open source

Abstract

Software bug analysis is one of the most important activities in Software Quality. The rapid and correct implementation of the necessary repair influence both developers, who must leave the fully functioning software, and users, who need to perform their daily tasks. In this context, if there is an incorrect classification of bugs, there may be unwanted situations. One of the main factors to be assigned bugs in the act of its initial report is severity, which lives up to the urgency of correcting that problem. In this scenario, we identified in datasets with data extracted from five open source systems (Apache, Eclipse, Kernel, Mozilla and Open Office), that there is an irregular distribution of bugs with respect to existing severities, which is an early sign of misclassification. In the dataset analyzed, exists a rate of about 85% bugs being ranked with normal severity. Therefore, this classification rate can have a negative influence on software development context, where the misclassified bug can be allocated to a developer with little experience to solve it and thus the correction of the same may take longer, or even generate a incorrect implementation. Several studies in the literature have disregarded the normal bugs, working only with the portion of bugs considered severe or not severe initially. This work aimed to investigate this portion of the data, with the purpose of identifying whether the normal severity reflects the real impact and urgency, to investigate if there are bugs (initially classified as normal) that could be classified with other severity, and to assess if there are impacts for developers in this context. For this, an automatic classifier was developed, which was based on three algorithms (Näive Bayes, Max Ent and Winnow) to assess if normal severity is correct for the bugs categorized initially with this severity. The algorithms presented accuracy of about 80%, and showed that between 21% and 36% of the bugs should have been classified differently (depending on the algorithm), which represents somewhere between 70,000 and 130,000 bugs of the dataset.