On-line Resources on Free Text Plagiarism

The following are a selection of articles available online which discuss free-text plagiarism and tools for detecting free-text plagiarism.

Joanna Bull, Carol Collins, Elisabeth Coughlin and Dale Sharp (2001). Technical Review of Plagiarism Detection Software. University of Luton and JISC Plagiarism Advisory Service.

This report deals with evaluating plagiarism detection software from both a user and technical viewpoint. The software reviewed was concerned with free-text detection and the aim of the report is to determine which program or service would be most useful for a university to use as part of its anti-plagiarism strategy. This report compares in detail the Turnitin, Findsame, Eve2, CopyCatch and WordCHECK packages.

Paul Clough (2000). Plagiarism in Natural and Programming Languages: an Overview of Current Tools and Technologies. University of Sheffield.

This report discusses in detail techniques used to hide plagiarism, legal aspects of proving that suspected plagiarism has taken place, and some of the tools available for detecting plagiarism.

Gill Chester (2001). Pilot of Free-text Electronic Plagiarism Detection Software. Joint Information Systems Committee.

This paper details a pilot of the ‘turnitin’ software across five universities throughout the UK. The pilot was organised at some universities in such a way that it was not compulsory for students to submit work electronically and therefore it was not compulsory to allow your work to be checked by the software.

Raphael A. Finkel, Arkady Zaslavsky, Krisztian Monostori and Heinz Schmidt (2002). Signature Extraction for Overlap Detection in Documents . Monash University, Australia.

This paper details a method for creating a signature for a document that is significantly smaller than the original document in order to speed up the process of determining which files are likely to be related. Documents that are likely to be similar can then be submitted to more accurate methods such as the MatchDetectReveal system at Monash, significantly reducing the time taken to compare documents against a large library of previously submitted work.

Timothy C. Hoad and Justin Zobel (2003). Methods for Identifying Versioned and Plagiarised Documents. Journal of the American Society for Information Science and Technology 54(3) pp. 203-215.

This paper compares and evaluates two main methods for identifying similarities between natural language documents: a fingerprinting approach whereby documents are initially compared using only small parts of their content and an information retrieval approach using the author’s own ‘identity measure’ to establish a ranking of documents in order of similarity. The paper is very thorough in its investigation, considering a number of alternatives in both methods before evaluating their effectiveness.

Krisztian Monostori, Arkady Zaslavsky and Alejandro Bia (2001). Using the MatchDetectReveal System for Comparative Analysis of Texts Monash University, Australia.

This paper contains details of the MatchDetectReveal system employed at Monash University. The system was designed primarily as a free-text plagiarism detector but it has also been used for information organisation applications such as linking cross-references in texts and organising collections of short works such as poems. The comparison works by parsing documents into suffix trees and using a previously developed algorithm to compare them.

Daniel White and Mike Joy (2004). “Sentence-based Natural Language Plagiarism Detection”. Journal on Educational Resources in Computing (JERIC) 4(4).

This paper describes an algorithm developed for detecting free-text plagiarism. The implemented algorithm has also been used to successfully detect plagiarism on real assignments.