Jurnal Ilmiah Kursor
Vol 6 No 1 (2011)

DETEKSI KEBERADAAN KALIMAT SAMA SEBAGAI INDIKASI PENJIPLAKAN DENGAN ALGORITMA HASHING BERBASIS N-GRAM

Diana Purwitasari (Lab Semantik Web, Teknik Informatika, ITS)
Putu Yuwono Kusmawan (Lab Semantik Web, Teknik Informatika, ITS)
Umi Laili Yuhana (Lab Semantik Web, Teknik Informatika, ITS)



Article Info

Publish Date
18 Jan 2011

Abstract

Abundant cases of plagiarism committed by some intellectual people in the Indonesia’s education fields have became such tragedy. Due to the amount of information which is available online are things that make copy-paste without proper citation cause plagiarism. This paper discusses about how to detect similar sentences which is probable caused by copy-paste. However plagiarism detection still needs further examination such as the existing of citation or not. Winnowing algorithm is used for detecting similar sentences between text files which is treated as a common subsequence problem. The algorithm finds document fingerprinting by changing sequence of N-grams from text into a set of hash values. If copy-paste sentences are found then both of text files must have the same document fingerprinting. Experiment has been done to observe the capability of detecting similar sentences by analyzing on value variations of n-gram, prime base b for hashing, window w, and threshold for determining plagiarism indication.

Copyrights © 2011






Journal Info

Abbrev

kursor

Publisher

Subject

Computer Science & IT Decision Sciences, Operations Research & Management

Description

Jurnal Ilmiah Kursor is published in January 2005 and has been accreditated by the Directorate General of Higher Education in 2010, 2014, 2019, and until now. Jurnal Ilmiah Kursor seeks to publish original scholarly articles related (but are not limited) to: Computer Science. Computational ...