NRFixer: Sentiment Based Model for Predicting the Fixability of Non-Reproducible Bugs

摘要

Software maintenance is an essential step in software development life cycle. Nowadays, softwarecompanies spend approximately 45% of total cost in maintenance activities. Large software projectsmaintain bug repositories to collect, organize and resolve bug reports. Sometimes it is difficultto reproduce the reported bug with the information present in a bug report and thus this bug ismarked with resolution non-reproducible (NR). When NR bugs are reconsidered, a few of themmight get fixed (NR-to-fix) leaving the others with the same resolution (NR). To analyse thebehaviour of developers towards NR-to-fix and NR bugs, the sentiment analysis of NR bug reporttextual contents has been conducted. The sentiment analysis of bug reports shows that NR bugs’sentiments incline towards more negativity than reproducible bugs. Also, there is a noticeableopinion drift found in the sentiments of NR-to-fix bug reports. Observations driven from thisanalysis were an inspiration to develop a model that can judge the fixability of NR bugs. Thusa framework, NRFixer, which predicts the probability of NR bug fixation, is proposed. NRFixer wasevaluated with two dimensions. The first dimension considers meta-fields of bug reports (model-1)and the other dimension additionally incorporates the sentiments (model-2) of developers forprediction. Both models were compared using various machine learning classifiers (Zero-R, Na?veBayes, J48, random tree and random forest). The bug reports of Firefox and Eclipse projects wereused to test NRFixer. In Firefox and Eclipse projects, J48 and Na?ve Bayes classifiers achievethe best prediction accuracy, respectively. It was observed that the inclusion of sentiments inthe prediction model shows a rise in the prediction accuracy ranging from 2 to 5% for variousclassifiers.