The toolbox for local and global plagiarism detection

Digital plagiarism is a problem for educators all over the world. There are many software tools on the market for uncovering digital plagiarism. Most of them can work only with text submissions. In this paper, we present a new architecture for a plagiarism detection tool that can work with many different kinds of digital submissions, from plain or formatted texts to audio podcasts. The open architecture is based on converting the digital submission into text form for processing by a plagiarism detection algorithm. To process non-text submissions, the system is extended with the appropriate converter. Such an open architecture makes the anti-plagiarism toolbox universal and easily adaptable for processing virtually any kind of digital submissions. This paper describes a software prototype based on the proposed architecture and presents the results of its implementation on a large archive of student papers. © 2008 Elsevier Ltd. All rights reserved.