Supporting Learning Information System through Knowledge Management Optimization using Long Short-Term Memory Method

Abstract

Effective information and knowledge management is vital in many areas, including higher education. The use of artificial intelligence (AI) technology, especially the long short-term memory (LSTM) information system performance patterns in the educational world. This article explores the application of LSTM to optimize knowledge management in colleges, focusing on the prediction of information systems performance. The proposed methods include text classification steps, with measures such as data collection, data pre-processing, word representation, classification, and evaluation. The test results showed that the LSTM model managed to classify reviews labeled positive, neutral, and negative with an accuracy of 33.33%. However, the success of the model was limited by the size of the data set and the pre-processing involved. This research recommends further development with the addition of experimental data, proper preprocessing adjustments, and better hyperparameter identification to improve the accuracy of the prediction results.
 Keywords: information management, artificial intelegence, LSTM, text classification, knowledge management, accurate prediction