A Program Plagiarism Detection Model Based on Information Distance and Clustering

Plagiarism in students programming assignment submissions causes considerable difficulties for course designers. Efficient detection of plagiarism in programming assignments of students is important to the educational procedure. This paper proposes a metric, based on information distance, to measure similarity between two programs. Furthermore, clustering analysis, based on shared near neighbors, is applied in order to provide more beneficial and detailed information about the program plagiarism. Experimental results demonstrate that our software has clear advantages over other plagiarism detection systems and it is quite beneficial to teachers to get rid of time-consuming and toilsome tasks. Key words: Program plagiarism, Detection, Information distance, Clustering