<![CDATA[Indonesia is rich in ethnic and cultural diversity, each reflected in its unique linguistic characteristics. One way to preserve the Javanese language is by conducting research on its dialects. This study aims to classify three main dialects in Java Island—East Java, Central Java, and West Java—using text data from online sources. The classification process includes preprocessing (tokenizing, case folding, and word weighting), data balancing with the Synthetic Minority Oversampling Technique (SMOTE), and classification using the K-Nearest Neighbor (K-NN) algorithm. This study highlights the importance of dialect recognition in supporting the preservation of the Javanese language and the development of linguistic technology applications. Testing using 10-fold cross-validation showed the best performance at , with an accuracy of 94.05%, precision of 95.83%, and recall of 94.44%. These findings significantly support computational linguistics research and the preservation of regional languages.]]>
Copyrights © 2024
