出版社：Indonesia Association of Computational Linguistics (INACL)
摘要：Plagiarism in writing is often found in various media, one of which is the internet. Prevention can be done by creating an intelligent system capable of detecting text. One of the algorithms used to create a text finding system is the Ratcliff/Obershelp algorithm. This algorithm combines a string of 2 pieces of text to get the total character length (sequence (string) matching). The results are used to search for similar words ( sub-sequence ) and calculate the character length. The calculation of the similarity value and the percentage is carried out to classify the types of plagiarism that exist in the text. The data used are 8 Indonesian news texts with different internet sources which are divided into 2 topics and the average error percentage is 0.26%.
