Publication Type

Journal Article

Version

submittedVersion

Publication Date

7-2022

Abstract

Bug localization is a recurrent maintenance task in software development. It aims at identifying relevant code locations (e.g., code files) that must be inspected to fix bugs. When such bugs are reported by users, the localization process become often overwhelming as it is mostly a manual task due to incomplete and informal information (written in natural languages) available in bug reports. The research community has then invested in automated approaches, notably using Information Retrieval techniques. Unfortunately, reported performance in the literature is still limited for practical usage. Our key observation, after empirically investigating a large dataset of bug reports as well as workflow and results of state-of-the-art approaches, is that most approaches attempt localization for every bug report without considering the different characteristics of the bug reports. We propose DigBug as a straightforward approach to specialized bug localization. This approach selects pre/post-processing operators based on the attributes of bug reports; and the bug localization model is parameterized in accordance as well. Our experiments confirm that departing from “one-size-fits-all” approaches, DigBug outperforms the state-of-the-art techniques by 6 and 14 percentage points, respectively in terms of MAP and MRR on average.

Keywords

Bug characteristics, Bug localization, Bug report, Fault localization, Information retrieval, Operator combination

Discipline

Software Engineering

Publication

Journal of Systems and Software

Volume

189

First Page

1

Last Page

16

ISSN

0164-1212

Identifier

10.1016/j.jss.2022.111300

Publisher

Elsevier

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1016/j.jss.2022.111300

Download

Share

COinS