Login | Register

Bug Triaging with High Confidence Predictions

Title:

Bug Triaging with High Confidence Predictions

Sarkar, Aindrila (2019) Bug Triaging with High Confidence Predictions. Masters thesis, Concordia University.

[thumbnail of Sarkar_MASc_S2020.pdf]
Preview
Text (application/pdf)
Sarkar_MASc_S2020.pdf - Accepted Version
651kB

Abstract

Correctly assigning bugs to the right developer or team, i.e., bug triaging, is a costly activity. A concerted effort at Ericsson has been done to adopt automated bug triaging to reduce development
costs. We also perform a case study on Eclipse bug reports. In this work, we replicate the research approaches that have been widely used in the literature including FixerCache. We apply them on
over 10k bug reports for 9 large products at Ericsson and 2 large Eclipse products containing 21 components. We find that a logistic regression classifier including simple textual and categorical attributes of the bug reports has the highest accuracy of 79.00% and 46% on Ericsson and Eclipse bug reports respectively.
Ericsson’s bug reports often contain logs that have crash dumps and alarms. We add this information to the bug triage models. We find that this information does not improve the accuracy of bug
triaging in Ericsson’s context. Eclipse bug reports contain the stack traces that we add to the bug triaging model. Stack traces are only present in 8% of bug reports and do not improve the triage accuracy.
Although our models perform as well as the best ones reported in the literature, a criticism of bug triaging at Ericsson is that accuracy is not sufficient for regular use. We develop a novel approach
that only triages bugs when the model has high confidence in the triage prediction. We find that we improve the accuracy to 90% at Ericsson and 70% at Eclipse, but we can make predictions for 62%
and 25% of the total Ericsson and Eclipse bug reports,respectively.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science
Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Sarkar, Aindrila
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Software Engineering
Date:2 December 2019
Thesis Supervisor(s):Rigby, Peter
ID Code:986157
Deposited By: Aindrila Sarkar
Deposited On:26 Jun 2020 13:36
Last Modified:26 Jun 2020 13:36
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top