<![CDATA[The use of information technology in the personnel administration process plays an active role in improving public services for civil servants (ASN) in the Cirebon City Government by providing accurate data for decision-making. One of the smart city applications that assists ASN in Cirebon City in supporting personnel administration activities is the SAMPEAN Cirebon City application. However, to ensure that this application is truly effective and meets user needs, it is important to analyze user reviews provided through application reviews. One effective method for analyzing user reviews is by using Natural Language Processing (NLP) and machine learning techniques. The NLP technique and classification model used is the KNN algorithm. The purpose of this research is to provide valuable input for application developers in improving the quality and performance of the SAMPEAN application. The research results show that by testing accuracy using the confusion matrix with K values of 3, 5, 7, and 9, it was found that K=9 provides the best performance with a balance between precision, recall, F1-Score, and accuracy. The model achieved a precision of 64%, recall of 90%, F1-Score of 75%, and accuracy of 62%. It can be concluded that with the optimization of the K parameter in KNN, the higher the K value, the higher the accuracy. This emphasizes the importance of selecting the right parameters to enhance the effectiveness of machine learning models in various Natural Language Processing (NLP) applications.]]>
Copyrights © 2024
