<![CDATA[With the development of information technology, especially in the legal field, legal case analysis can now be done more efficiently through the application of machine learning. This study aims to classify legal cases based on the status of Cited and Uncited using the K-Nearest Neighbor (KNN) algorithm. The classification process includes text preprocessing stages, word weighting using the TF-IDF method, and testing the KNN algorithm with various values of the parameter k. The research data was taken from the Federal Court of Australia (FCA) covering legal cases from 2006–2009, with three data sharing scenarios: 90:10, 80:20, and 70:30. The evaluation model was carried out using a confusion matrix with metrics of accuracy, precision, recall, and F1-score. The best results were obtained in the 80:20 scenario with a value of k = 3, resulting in an accuracy of 96.36%, a precision of 96.80%, a recall of 99.49%, and an F1-score of 98.13%. With these results, the KNN algorithm is proven to be effective in supporting the automatic legal document classification process.]]>
Copyrights © 2025
