Page 138 - Conference Book The 3rd IConVET "Future of TVET Graduates: Developing Talent for Industry 4.0 and The New Normal"

The 3 International Conference
rd
on Vocational Education and Technology (IConVET)
Universitas Pendidikan Ganesha - Bali | 7 November, 2020
th
COMPARISON OF THE BM25 AND RABIN KARP
ALGORITHM FOR PLAGIARISM DETECTION

1
I Nyoman Saputra Wahyu Wijaya , Ketut Agus Seputra , Wayan Gede Suka
2
Parwita 3
1,2 Department of Informatics Engineering, Faculty of Engineering and Vocational,
Universitas Pendidikan Ganesha

3 Teknik Informatika, STMIK STIKOM Indonesia, Denpasar, Bali, Indonesia

1
Email: wahyu.wijaya@undiksha.ac.id , agus.seputra@undiksha.ac.id ,
2
gede.suka@gmail.com
3
Abstract. Plagiarism occurs because of the easy distribution of data.
Plagiarism detection of documents such as student assignments and final
projects requires a long process, often overlooked. However, to avoid
plagiarism, a document must be checked for the level of plagiarism.
Plagiarism detection can be done online / offline with the plagiarism
checker. However, checking documents with plagiarism checkers such as
Turnitin, Dupli Checker, Copyleaks, PaperRater, Grammarly and others
requires additional fees. Several studies have been conducted to detect
plagiarism. BM25 and Rabin Karp are examples of the Plagiarism Checker
method. BM25 is tf idf based, while Rabin Karp is Hashing based. Each
method needs to know its performance to detect plagiarism. Based on these
problems, a study on the comparison of plagiarism detection with the BM25
algorithm with Rabin-Karp will be conducted. The case study is to use the
article in Indonesian. The application of the BM25 and Rabin Karp
algorithms goes through the Pre-Processing stage which consists of case
folding, cleaning, tokenizing, filtering, and stemming. In this study, we used
sastrawi stemmer. The test was conducted on twenty articles in Indonesian.
The test results that are seen are the performance in the form of execution
time.

| IConVET 2020 | 138

https://conference.undiksha.ac.id/iconvet/ | 138 |