<![CDATA[SIMAK Unismuh Makassar is an important platform used by students to submit suggestions and criticisms related to various academic aspects. In this study, researchers implemented the Recurrent Neural Network (RNN) algorithm to classify suggestions and criticisms received through SIMAK Unismuh. The purpose of this study was to determine the implementation of the RNN Algorithm in classifying suggestions and criticisms on the SIMAK Unismuh page and how successful the RNN Algorithm was in classifying suggestions and criticisms on the SIMAK Unismuh page. RNN was chosen because of its ability to process sequential text data, such as input in the form of sentences, which allows the model to capture the context of the input more effectively. The dataset used in this study consists of a number of suggestion and criticism data that have been categorized manually. The RNN model that was built was then trained and tested using the data to assess its accuracy and performance. The results showed that the model achieved the highest accuracy of 91% and the lowest accuracy of 90%. Although there were variations in model performance, these results indicate that RNN has good potential in classifying suggestion and criticism texts. The RNN model can help institutions understand and respond to user input more effectively, although it still requires further optimization to improve the consistency and accuracy of the results. The conclusion of this study shows that the RNN model is able to classify suggestions and criticisms with an adequate level of accuracy. The application of this model is expected to help the Unismuh administration in managing student input more efficiently, as well as providing more appropriate and faster responses to academic needs.Keywords: Text Classification, Recurrent Neural Network (RNN), SIMAK Unismuh, Suggestions and Criticisms, Academic Information System.]]>
Copyrights © 2025
