Uncovering Plagiarism Networks

Abstract

Plagiarism detection in educational programming assignments is still a problematic issue in terms of resource waste, ethical controversy, legal risks, and technical complexity. This paper presents AC, a modular plagiarism detection system. The design is portable across platforms and assignment formats and provides easy extraction into the internal assignment representation. Multiple similarity measures have been incorporated, both existing and newly-developed. Statistical analysis and several graphical visualizations aid in the interpretation of analysis results. The system has been evaluated with a survey that encompasses several academic semesters of use at the authors' institution.