RANCANG BANGUN APLIKASI PENDETEKSIAN KESAMAAN PADA DOKUMEN TEKS MENGGUNAKAN ALGORITMA ENHANCED CONFIX STRIPPING DAN ALGORITMA WINNOWING

Muhammad Nur Khidfi (Jurusan Teknik Informatika, Fakultas Teknik, Universitas Halu Oleo, Kendari)
Isnawaty Isnawaty (Jurusan Teknik Informatika, Fakultas Teknik, Universitas Halu Oleo, Kendari)
Jayanti Yusmah Sari (Jurusan Teknik Informatika, Fakultas Teknik, Universitas Halu Oleo, Kendari)

SemanTIK : Teknik Informasi
Vol 4, No 2 (2018): semanTIK

With the development of technology, the increase of acts of plagiarism in the world of education. Many students who did plagiarism in doing their task, thesis etc. Therefore, an application that can detect the similarity between text documents is required. This research used Enhanced Confix Stripping (ECS) Stemmer algorithm for text stemming process and Winnowing algorithm to calculate the similarity between documents. By specifying the gram and window values of the Winnowing algorithm, it made easier for the user to use the application without being confused to determine the value of the gram and the window to produce an accurate equality value. From the test results 5 pairs of chapters 1 thesis of students who categorized together produced a similarity score of about 45-20%.Keywords: Enhanced Confix Stripping (ECS) Stemmer, Winnowing, Similarity, Plagiarism.DOI: 10.5281/zenodo.1407866