ABSTRACT
Predicting bug-fixing time helps software managers and teams prioritize
tasks, allocations and costs in software projects. In literature,
machine learning (ML) models have been proposed to predict bugfixing
time. One of features highlighted by studies is the reporter
(the person who open the bug) has positive influence in the time
to resolve a bug. In this way, this paper answers the following research
question: How does a collaborative filtering approach perform
in predicting bug-fixing time compared to the supervised machine
learning approaches? In order to answer this question we performed
an experiment using collaborative filtering approach to recommend
the bugs that are fast to be resolved in two open software projects.
We compare our proposed approach with the ML approach related
to the literature. As a result, the collaborative filtering approach
outperforms the supervised ML achieving an F-measure of 74%
while the supervised ML achieved 66%. The collaborative filtering
approach showed to be a new perspective to predict bug-fixing time
in software projects focusing the prediction on the reporter.