Detection of Plagiarism in University Projects Using Metrics-based Spectral Similarity

Abstract. An original method of spectral similarity analysis for plagiarism detection in university project is presented. The approach is based on a clone detection tool called CLAN that performs metrics based similarity analysis of source code fragments. Definitions and algorithms for spectral similarity analysis are presented and discussed. Experiments performed on university projects are presented. Experimental results include the distribution of similarity in C and C++ projects. Analysis of spectral similarity distribution identifies the most similar pairs of projects that can be considered as candidates for plagiarism. Keywords. plagiarism detection, software comparison, clone detection, spectral analysis, code metrics

• Type: Conference
• Year: 2006
• Where: DAGSTUHL
• Authors: Ettore Merlo
• Keywords: DAGSTUHL 2006, DAGSTUHL 2007, Similarity Analysis, Spectral Similarity, Spectral Similarity Analysis