<![CDATA[Plagiarism is a serious challenge in the academic world that threatens scientific integrity. Access to commercial plagiarism detection tools like Turnitin is often limited due to high costs, while free tools have word count limitations and data privacy issues. This research aims to develop an offline plagiarism detection application based on natural language processing using the term frequency-inverse document frequency (TF-IDF) and cosine similarity algorithms. This application is designed to operate without an internet connection and without word count limitations and guarantees data security. The development method uses Python 3.13 with the PySide6 framework for the user interface and SQLite as the database. The test results on 1 test document and 9 comparison documents show a detection accuracy with an overall score of 9.38% (SkLearn method). The processing time for each is 8.55 seconds. This application is expected to be an alternative solution for students and educational institutions in independently and safely detecting plagiarism.]]>
Copyrights © 2026
