Similarity Judul Tugas Akhir Menggunakan Metoda Cosine, Jaccard, Rabin-Karp Pada Jurusan TI

Plagiarism can occur anywhere and can be committed by anyone. For example, plagiarism by students when creating college assignments, where they unintentionally use someone else’s writing or ideas and forget to cite the source. Based on the above explanation, it is necessary to develop an information system to assess the percentage of plagiarism for proposed titles. After conducting an implementation test to measure the similarity accuracy and processing speed, a comparison was made between the proposed titles and the existing data, totaling 940 titles. The results showed a similarity rate of 84.13% with the Rabin-Karp method, 61.24% with the Cosine method, and 42.86% with the Jaccard method. In terms of processing speed, the Rabin-Karp method ranked first with a time of 0.5023 seconds, followed by the Cosine method with 0.5095 seconds, and the Jaccard method with 0.5103 seconds. From the test results, Jaccard Similarity is more suitable for short texts with unique word sets, but it is less precise for longer texts with important word distributions. Meanwhile, the Rabin-Karp method is not designed to measure general text similarity; instead, it is intended for fast and precise substring searches in pattern matching contexts