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
References
[1] Putra TI, Suprapto S, Bukhori AF. Model Klasifikasi Berbasis Multiclass Classification dengan Kombinasi Indobert Embedding dan Long Short-Term Memory untuk Tweet Berbahasa Indonesia. Jurnal Ilmu Siber dan Teknologi Digital. 2022 Nov 11;1(1):1-28.
[2] Saputra AW, Wibawa AP, Pujianto U, Utama AB, Nafalski A. LSTM-based Multivariate Time-Series Analysis: A Case of Journal Visitors Forecasting. ILKOM Jurnal Ilmiah. 2022 Apr;14(1):57–62.
[3] Pratama ED. Implementasi Model Long-Short Term Memory (LSTM) pada Klasifikasi Teks Data SMS Spam Berbahasa Indonesia [ JMLCI]. The Journal on Machine Learning and Computational Intelligence. 2022 Jul;1(2).
[4] Mahjoub S, Chrifi-Alaoui L, Marhic B, Delahoche L. Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks. Sensors (Basel). 2022 May;22(11):4062.
[5] Selvin S, Vinayakumar R, Gopalakrishnan EA, Menon VK, Soman KP. Stock price prediction using LSTM, RNN and CNN-sliding window model. In2017 international conference on advances in computing, communications and informatics (icacci) 2017 Sep 13 (pp. 1643-1647). IEEE.
[6] Wiranda L, Sadikin M. Penerapan Long Short Term Memory Pada Data Time Series Untuk Memprediksi Penjualan Produk Pt. Metiska Farma. Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI. 2019;8(3):184-96. Zhang Z, Qin H, Yao L, Lu J, Cheng L. Interval prediction method based on Long-Short Term Memorynetworks for system integrated of hydro, wind and solar power. Energy Procedia. 2019 Feb;158:6176–82.
[7] Sudriani Y, Ridwansyah IA, Rustini H. Long short term memory (LSTM) recurrent neural network (RNN) for discharge level prediction and forecast in Cimandiri river, Indonesia. InIOP Conference Series: Earth and Environmental Science 2019 Jul 29 (Vol. 299, p. 012037). IOP Publishing.
[8] Masri F, Saepudin D, Adytia D. Forecasting of Sea Level Time Series using Deep Learning RNN, LSTM, and BiLSTM, Case Study in Jakarta Bay, Indonesia. e- Proceeding Eng. 2020;7(2):8544-51.
[9] Wisyaldin MK, Luciana GM, Pariaman H. Pendekatan Long Short-Term Memory untuk Memprediksi Kondisi Motor 10 kV pada PLTU Batubara. J. Kilat. 2020;9(2):311–8.
[10] Afika R, Suprih W, Atikah DA, Fadlan BH. Next word prediction using lstm. Journal of Information Technology and Its Utilization. 2022 Jun;5(1):10–3.
[11] Zhang R. LSTM-based Stock Prediction Modeling and Analysis. In2022 7th International Conference on Financial Innovation and Economic Development (ICFIED 2022) 2022 Mar 26 (pp. 2537-2542). Atlantis Press.
[12] Rizki M, Basuki S, Azhar Y. Implementasi Deep Learning Menggunakan Arsitektur Long Short Term Memory Untuk Prediksi Curah Hujan Kota Malang. Repositor. 2020;2(3):331–8.
[13] Elsworth S, Güttel S. Time series forecasting using LSTM networks: A symbolic approach. arXiv preprint arXiv:2003.05672. 2020 Mar 12.
[14] Cahuantzi R, Chen X, Güttel S. A comparison of LSTM and GRU networks for learning symbolic sequences. InScience and Information Conference 2023 Jul 13 (pp. 771- 785). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-37963- 5_53.