Maximizing the Effectiveness of E-Learning Through Automated Grading and Comprehensive Plagiarism Detection Eka Larasati Amalia, Vivin Ayu Lestari, Vivi Nur Wijayaningrum, Moch Zawaruddin Abdullah, Niken Maharani Permata, and Anisatul Latifah
Politeknik Negeri Malang
Abstract
The use of technology in education has become imperative in the digital era. This study aims to develop and evaluate the effectiveness of an e-learning system that integrates comprehensive plagiarism detection using the Cosine Similarity method and automated grading features. The system is designed to detect similarities between student essay answers and reference answers, thereby enhancing academic integrity. The research methodology includes black box testing to assess system functionality and the System Usability Scale (SUS) to evaluate user perception. Testing results indicate that the system achieves high accuracy in plagiarism detection, with an average SUS score of 80.5%, signifying good user acceptance. The system is not only capable of identifying identical texts but also similar texts and paraphrases, making it an effective tool to support the learning process. Additionally, the automated grading feature enhances the efficiency of academic evaluation, reducing the time and effort required by educators. In conclusion, the integration of comprehensive plagiarism detection and automated grading features in the e-learning system significantly maximizes its effectiveness and integrity in academic assessments within educational institutions.
