Deteksi Plagiarisme Skripsi Mahasiswa dengan Metode Single-link Clustering dan Jaro-Winkler Distance

Abstract

Abstract— The rise of plagiarism is one of the negative impacts of the development of information and communication technology. Plagiarism can occur anywhere. One of the examples is a university with the object of plagiarism as a student's final project. So we need a system to detect plagiarism so that it can suppress plagiarism in the college environment. In detecting the similarity of a writing will be faster if the writing has been grouped before compared to each other. Single-link clustering was chosen because it has a simple algorithm and can be implemented without the initial cluster. In plagiarism plagiarism usually changes the sentence structure so that it looks different Jaro-Winkler distance is chosen because it can detect similarities in paragraphs that have been changed in sentence structure because Jaro-Winkler distance has a flexible indexing with theoretical distance so that a word or character is considered the same. The stages in this study include data collection, preprocessing, grouping writing with Single-link clustering, comparing writing with jaro-winkler distance, and testing with precision and recall. After testing, the average value of precision was 84.37% and recall was 84.37% with a level of plagiarism of 99.1%. Keywords—: jaro-winkler distance; plagiarisme; single-link clustering.

Pengaruh Synonym Recognition dalam Deteksi Kemiripan Teks Menggunakan Winnowing dan Cosine Similarity

“…In preprocessing, a series of steps were taken to remove parts of text that were not needed in a document because they would become noise in the subsequent process. Preprocessing is divided into three distinct stages: tokenizing, filtering, and stemming [18], [19].…”

Akurasi dalam Mengidentifikasi Tingkat Similarity pada Artikel Ilmiah Menggunakan Algorithma Jaro Winkler

“…Kesamaan suatu dokumen dengan dokumen lainnya atau suatu text dengan text lainnya dapat diketahui dengan menggunakan pendekatan string metric yaitu dengan melakukan perbandingan dua string. Kedua string tersebut dimasukkan ke dalam fungsi matematis tertentu untuk mengetahui jarak antara keduanya [3]. Menghitung jumlah kemiripan kata adalah tugas umum, namun memberikan peran yang sangat penting dalam berbagai aplikasi Natural Language Processing (NLP), seperti mesin pencari, detektor plagiarisme, sistem penjawab pertanyaan, dan lainnya [4].…”