Output details
11 - Computer Science and Informatics
University of Warwick
An approach to source-code plagiarism detection and investigation using latent semantic analysis
<17> Published in a leading computing journal, with a wide readership (researchers, developers, educators and technical managers), this paper presents the first successful application of an Information Retrieval approach to source code plagiarism detection. It addresses two recognised weaknesses in other techniques: programming language dependence and poor recall (non-detection). The paper has been cited by academic researchers from 11 countries, and has impacted on industry, including InfoSys Labs, Bangalore, India [Karnam, D. et al., Proc. ICSM 2012, 609-612] and Zeidman Consulting, Cupertino, USA [Baer, N. and Zeidman, R., JSEA, 5, 249-254, 2012]. It has already seeded a further journal publication (Informatica).