Deteksi Plagiarisme Dokumen Teks Menggunakan Algoritma Rabin-Karp Dengan Synonym Recognition

Dewanto, Sandy (2013) Deteksi Plagiarisme Dokumen Teks Menggunakan Algoritma Rabin-Karp Dengan Synonym Recognition. Sarjana thesis, Universitas Brawijaya.

Abstract

Plagiarisme merupakan ancaman yang cukup berbahaya dalam dunia akademik dan penulisan. Menjiplak karya orang lain dan mengakuinya sebagai karya pribadi termasuk dalam tindakan plagiarisme. Sistem deteksi plagiarisme dalam dokumen teks umumnya mengimplementasikan algoritma pencocokan string untuk mencari kesamaan kata (string) antar dokumen. Algoritma yang cukup baik dalam mendeteksi pola banyak adalah algoritma Rabin-Karp. Algoritma yang menerapkan fungsi hash ini terbukti cukup ampuh untuk mendeteksi plagiarisme lewat kesamaan kata. Dan melalui varian algoritma Rabin-Karp yang telah dimodifikasi, sistem tidak hanya membandingkan sisa modulo tetapi juga membandingkan hasil bagi terhadap modulo itu sendiri. Dengan cara ini bisa menghindari spurious hit (kesalahan dalam pencocokan). Sehingga bisa diperoleh presentase kesamaan dan waktu proses yang lebih baik. Dan untuk mengantisipasi kata yang diganti dengan sinonimnya digunakan pendekatan synonym recognition. Meskipun menambah waktu komputasi metode algoritma Rabin-Karp dengan synonym recognition mampu meningkatkan presentase kesamaan daripada tanpa synonym recognition.

English Abstract

Plagiarism is a pretty dangerous threat in the academic and writing field. The act of plagiarism includes taking other peoples work and claiming it for personal work. Text document Plagiarism detection systems are generally implementing string matching algorithm to find the similarity of words (strings) between documents. Algorithm that has quite good reputation at detecting multiple patterns is Rabin-Karp algorithm. This Algorithm is implementing hash functionand proved powerful enough to detect plagiarism through word similarity. And by the modified Rabin-Karp algorithm variant, the system not only compare the remain yet also compare the quotient by by the mod as well. In this way the systems could avoid spurious hits (error in matching). So the better percentage of similarity and processing time can be obtained. And to anticipate the words that changed by synonym used Synonym recognition approach. Though it‟s burdening in computational time Rabin-Karp algorithm method with synonym recognition is able to increase the percentage of similarity than without one.

Item Type: Thesis (Sarjana)
Identification Number: SKR/FTIK/2013/153/051307723
Subjects: 000 Computer science, information and general works > 005 Computer programming, programs, data
Divisions: Fakultas Ilmu Komputer > Teknik Informatika
Depositing User: Hasbi
Date Deposited: 28 Nov 2013 08:58
Last Modified: 23 Oct 2021 09:33
URI: http://repository.ub.ac.id/id/eprint/145787
[thumbnail of BAB_II_.pdf]
Preview
Text
BAB_II_.pdf

Download (2MB) | Preview
[thumbnail of BAB_V.pdf]
Preview
Text
BAB_V.pdf

Download (2MB) | Preview
[thumbnail of BAB_I.pdf]
Preview
Text
BAB_I.pdf

Download (1MB) | Preview
[thumbnail of BAB_VI.pdf]
Preview
Text
BAB_VI.pdf

Download (1MB) | Preview
[thumbnail of BAB_IV.pdf]
Preview
Text
BAB_IV.pdf

Download (2MB) | Preview
[thumbnail of BAB_III.pdf]
Preview
Text
BAB_III.pdf

Download (2MB) | Preview
[thumbnail of Cover_&_Daftar_Isi.pdf]
Preview
Text
Cover_&_Daftar_Isi.pdf

Download (1MB) | Preview
[thumbnail of Daftar_Pustaka.pdf]
Preview
Text
Daftar_Pustaka.pdf

Download (1MB) | Preview

Actions (login required)

View Item View Item