E-Learning Keyword Search Optimization Using Machine Learning Algorithms

Abstract

The rise of e-learning technologies in the past few decades has completely changed how people acquire and interact with educational resources. Because there is so much useful data accessible on the internet, it is essential to optimize keyword searches effectively to make certain individuals find the resources they need quickly. The present research examined the efficacy of processing approaches such as tokenization and extracting features utilizing learning to rank (LTR), as well as e-learning search optimization approaches utilizing support vector machines (SVM), naive bayes, and neural networks. The multi-platform online courses data that the authors downloaded from the Kaggle database to do the tests are utilized. According to findings, SVM combined with tokenization and LTR produced higher quality outcomes than other approaches in terms of precision, accuracy, recall, and F1 score.