We are developing new techniques for analysing collections of files containing program source code, in order to identify similarities amongst the files and hence detect potential plagiarism, including the application of string algorithms, and the use of Latent Semantic Analysis (LSA). We are interested in both the theoretical background to plagiarism and the technical aspects of tool development.

Recent work has concentrated on what is actually meant by plagiarism with several recently published papers. We have also undertaken surveys to ascertain how plagarism is perceived by both students and academic staff. This work has resulted in a new definition of source-code plagiarism in an academic context. We are now working to deepen understanding of a variety of plagiarism issues and further develop our software tools.

Plagiarism Detection Software - Sherlock and PlaGate

We are also developing tools to support the detection of plagiarism. One tool which has been under development for some time is the Sherlock plagiarism detection software, which can be used for intra-corpal collection of either source code or plain-text. Java is the main supported programming language but the tool also support most procedural or object-oriented languages.

In addition to Sherlock, we have more recently been developing a novel tool called PlaGate. PlaGate accepts as input a corpus of files and a set of source-code fragments and presents graphical output that indicates the relative importance of the given source-code fragments across files in a corpus.

The tool categorises source-code fragments based on their importance as evidence towards proving plagiarism. This is done by using LSA to detect how important they are within the specific files under investigation in relation to other files in the corpus. The tool works alongside current plagiarism detection tools and can also be used to detect similar source-code files that could have been missed by other tools.

Publications

Cosma, G. and Joy, M.S. (2012) An Approach to Source-Code Plagiarism Detection and Investigation using Latent Semantic Analysis. IEEE Transactions on Computers, 61 (3). pp. 379-394. (BibTeX)

Joy, M.S. and Cosma, G. and Yau, J.Y-K. and Sinclair, J.E. (2011) Source Code Plagiarism - a Student Perspective. IEEE Transactions on Education, 54 (1). pp. 125-132. ISSN 0018-9359 (BibTeX)

Mozgovoy, M. and Kakkonen, T. and Cosma, G. (2010) Automatic Student Plagiarism Detection: Future Perspectives. Journal of Educational Computing Research. (In Press) (BibTeX)

Joy, M.S. and Cosma, G. and Sinclair, J.E. and Yau, J.Y-K. (2009) A Taxonomy of Plagiarism in Computer Science. In: International Conference on Education and New Learning Technologies (EDULEARN09), 6-8 Jul 2009, Barcelona, Spain. [PDF] (BibTeX)

Cosma, G. (2008) An Approach To Source-code Plagiarism Detection And Investigation Using Latent Semantic Analysis. PhD thesis, University of Warwick. [PDF] (BibTeX)

Cosma, G. and Joy, M.S. (2008) Towards a Definition on Source-Code Plagiarism. IEEE Transactions on Education, 51 (2). pp. 195-200. [PDF] (BibTeX)

Cosma, G. and Joy, M.S. (2006) Source-code Plagiarism: a UK Academic Perspective. Technical Report. University of Warwick, Coventry. [PDF] (BibTeX)

Cosma, G. and Joy, M.S. (2006) Source-code Plagiarism: a UK Academic Perspective. In: 7th Annual Conference of the HEA Network for Information and Computer Sciences, 29-31 August 2006, Dublin, Eire. [PDF] (BibTeX)

Mozgovoy, M. and Frederiksson, K. and White, D.R. and Joy, M.S. and Sutinen, E. (2005) Fast Plagiarism Detection System. In: String Processing and Information Retrieval: 12th International Conference (SPIRE 2005). LNCS (3772). Springer, London, pp. 267-270. (BibTeX)

White, D.R. and Joy, M.S. (2004) Sentence-Based Natural Language Plagiarism Detection. ACM Journal on Educational Resources in Computing, 4 (4). pp. 1-20. [PDF] (BibTeX)

Joy, M.S. and Luck, M. (1999) Plagiarism in Programming Assignments. IEEE Transactions on Education, 42 (2). pp. 129-133. ISSN 0018-9359 [PDF] (BibTeX)

Joy, M.S. and Luck, M. (1998) Plagiarism in Programming Assignments. Technical Report. University of Warwick, Coventry. [PDF] (BibTeX)