Write a Blog >>
ESEC/FSE 2021
Thu 19 - Sat 28 August 2021 Clowdr Platform

Authorship attribution (i.e., determining who is the author of a piece of source code) is an established research topic. State-of-the-art results for the authorship attribution problem look promising for the software engineering field, where they could be applied to detect plagiarized code and prevent legal issues.
With this article, we first introduce a new language-agnostic approach to authorship attribution of source code.
Then, we discuss limitations of existing synthetic datasets for authorship attribution, and propose a data collection approach that delivers datasets that better reflect aspects important for potential practical use in software engineering.
Finally, we demonstrate that high accuracy of authorship attribution models on existing datasets drastically drops when they are evaluated on more realistic data. We outline next steps for the design and evaluation of authorship attribution models that could bring the research efforts closer to practical use for software engineering.

Thu 26 Aug

Displayed time zone: Athens change

09:00 - 10:00
Analytics & Software Evolution—Mining Software RepositoriesJournal First / Research Papers +12h
Chair(s): Juri Di Rocco University of L'Aquila
09:00
10m
Paper
Characterizing Search Activities on Stack Overflow
Research Papers
Jiakun Liu Zhejiang University, Sebastian Baltes University of Adelaide, Christoph Treude University of Adelaide, David Lo Singapore Management University, Yun Zhang Zhejiang University City College, Xin Xia Huawei Technologies
DOI
09:10
10m
Paper
Authorship Attribution of Source Code: A Language-Agnostic Approach and Applicability in Software Engineering
Research Papers
Egor Bogomolov JetBrains Research; HSE University, Vladimir Kovalenko JetBrains Research, Yurii Rebryk HSE University, Alberto Bacchelli University of Zurich, Timofey Bryksin JetBrains Research; HSE University
DOI Pre-print
09:20
5m
Paper
Insights into Non-Merged Pull Requests in GitHub: Is there Evidence of Bias Based on Perceptible Race
Journal First
Reza Nadri University of Waterloo, Gema Rodríguez-Pérez University of Waterloo, Mei Nagappan University of Waterloo
09:25
5m
Paper
Automatic Recovery of Issue Type Labels
Journal First
Farida El Zanaty McGill University, Christophe Rezk McGill University, Sander Lijbrink Shopify, Inc., Willem Van Bergen Shopify, Inc., Mark Côté Shopify, Inc., Shane McIntosh McGill University
09:30
30m
Live Q&A
Q&A (Analytics & Software Evolution—Mining Software Repositories)
Research Papers

21:00 - 22:00
Analytics & Software Evolution—Mining Software RepositoriesResearch Papers / Journal First
Chair(s): Phuong T. Nguyen University of L’Aquila, Venera Arnaoudova Washington State University
21:00
10m
Paper
Characterizing Search Activities on Stack Overflow
Research Papers
Jiakun Liu Zhejiang University, Sebastian Baltes University of Adelaide, Christoph Treude University of Adelaide, David Lo Singapore Management University, Yun Zhang Zhejiang University City College, Xin Xia Huawei Technologies
DOI
21:10
10m
Paper
Authorship Attribution of Source Code: A Language-Agnostic Approach and Applicability in Software Engineering
Research Papers
Egor Bogomolov JetBrains Research; HSE University, Vladimir Kovalenko JetBrains Research, Yurii Rebryk HSE University, Alberto Bacchelli University of Zurich, Timofey Bryksin JetBrains Research; HSE University
DOI Pre-print
21:20
5m
Paper
Insights into Non-Merged Pull Requests in GitHub: Is there Evidence of Bias Based on Perceptible Race
Journal First
Reza Nadri University of Waterloo, Gema Rodríguez-Pérez University of Waterloo, Mei Nagappan University of Waterloo
21:25
5m
Paper
Automatic Recovery of Issue Type Labels
Journal First
Farida El Zanaty McGill University, Christophe Rezk McGill University, Sander Lijbrink Shopify, Inc., Willem Van Bergen Shopify, Inc., Mark Côté Shopify, Inc., Shane McIntosh McGill University
21:30
30m
Live Q&A
Q&A (Analytics & Software Evolution—Mining Software Repositories)
Research Papers