 |
 |
 |
Research
Interests
Publications
Corpora
Teaching
RMIT University
Melb University
Doctor of Philosophy
I commenced my PhD at RMIT city campus in February 2007 and plan to submit my thesis in mid-2010. Highlights to date include chairing the 2007 CS&IT Research Students Conference and four awards for various conference papers and presentations. Publications to date can be found on my publications page. More information about the Doctor of Philosophy program program can be found here.
Above: Search Engines Group Barbeque 2007: Milad, Sarvnaz, Nik, Falk, Steven, Ying, Jelita and Ranjan.
Thesis
Title
Source Code Authorship Attribution
Abstract
To attribute authorship means to identify the correct author among many
candidates for samples of work of unknown or contentious authorship.
Authorship attribution is a prolific research area for natural language,
but much less so for source code with limited research groups having
published empirical results concerning the accuracy of their software.
This research aims to initially survey, implement and benchmark all
existing methodologies to establish a consistent set of authorship
attribution accuracy scores using newly constructed, significant source
code corpora made up of academic sources, industry sources and multiple
programming languages. Next, a novel information retrieval methodology
will be proposed, implemented and evaluated against the existing works
to demonstrate the accuracy of this alternative and overcome previous
shortcomings. Finally, the accuracy of the new methodology will be
explored in the context of author style changing over time by
experimenting with a corpus of student programming assignments that span
three semesters of their career. The outcomes will suggest the amount of
time necessary for individual coding styles to stabilise which is
essential knowledge for ongoing authorship attribution studies and
quality control in general.
| Last modified: 17/01/2010 |
|
|
|
|