Hermetic and Web Plagiarism Detection Systems for Student Essays—An Evaluation of the State-of-the-Art

• DOI: 10.2190/ec.42.2.a
• Publication Date: 2010-02-11T02:03:57Z
• Authors: Tuomo Kakkonen; Maxim Mozgovoy
• Keywords: Plagiarism detection; Categorical variable; Empirical Research

Plagiarism has become a serious problem in education, and several plagiarism detection systems have been developed for dealing with this problem. This study provides an empirical evaluation of eight student essays. We present categorical hierarchy the most common types that are encountered texts. Our purpose-built test set contains texts which instances commonly utilized plagiaristic techniques embedded. While Sherlock was clearly overall best hermetic system, SafeAssignment performed detecting web plagiarism. TurnitIn found to be advanced system semi-automatic forms such as substitution Cyrillic equivalents certain characters or insertion fake whitespaces. The survey indicates none capable reliably from both local Internet sources while at same time being able identify technical tricks plagiarizers use conceal