Enhanced Keyword Search Optimization in E-Learning Using Machine Learning Models

Multi-keyword search functionality as an enhancement to e-learning systems may facilitate the retrieval of instructional resources more efficiently, according to this study. It is more essential than ever for students to be able to efficiently navigate digital materials, as an increasing number of institutions offer online courses. To achieve this, researchers employ a combination of sophisticated machine learning models and preprocessing techniques, including TF-IDF and Named Entity Recognition (NER), as well as Decision Trees (DT), Random Forest (RF), and Gradient Boosting Machines (GBM). The efficacy of the Decision Tree model, which integrates TF-IDF and NER, has been ascertained through exhaustive testing and evaluation. The system attains an exceptional accuracy rate of 98.45%. The results of the research are additionally corroborated by the high $\mathbf{F 1}$ scores of $\mathbf{0. 9 3}$ for overall model performance, $\mathbf{0. 9 6}$ for precision, and 0.98 for recall. The results of this study underscore the importance of integrating sophisticated search techniques into e-learning platforms to guarantee that users can obtain tailored and efficient learning experiences. The findings from this research enhance the visibility and pertinence of scholarly materials, thereby supporting the continuous expansion of online education platforms.