Content-based Plagiarism Detection in Korean Document Using Ferret’s Trigram

Document plagiarism means the unauthorized use of the original document of another author without recognition of the source. With the development of the Internet, the volume of digital information available and easily accessible has increased massively and detecting plagiarism manually is so expensive in terms of both time and effort. Although many copy detection techniques for digital document already have been released, their performance is still unsatisfactory. This paper proposes content-based copy detection for Hangul (Korean character) documents by improving the detection accuracy of existing Ferret’s trigram. The key of the proposed system to identify plagiarism is to use two elements: firstly the number of matching trigrams in the original document and secondly the weighting factor of the trigrams where they match sequentially. In this study we show that the proposed system is developed further by weighting results depending on the matching degree of trigram, thereby improving the accuracy of similarity detection in Hangul documents.