文章基本信息

标题：Improving Learning Style Prediction using Tree-based Algorithm with Hyperparameter Optimization
本地全文：下载
作者：Haziqah Shamsudin ; Umi Kalsom Yusof ; Maziani Sabudin 等
期刊名称：International Journal of Advances in Soft Computing and Its Applications
印刷版ISSN：2074-8523
出版年度：2020
卷号：12
期号：1
页码：65-80
出版社：International Center for Scientific Research and Studies
摘要：Learning style of specific users in an online learning system isdetermined based on their interaction and behavior towards the system.The most common online learning theory used in determining thelearning style is the Felder-Silvermans Theory. Many researchers haveproposed machine learning algorithms to establish learning style byusing log file attributes. However, they did not optimize the parametersselections which also contribute to low performance matrices. In thispaper, tree-based algorithm is being used to detect the learning style ofthe user. The tree-based algorithms used in this paper are the DecisionTree (CART), Random Forest (RF), and Extreme Gradient Boosting(Xgb). In order to optimize the results of the performance matrices, theparameters of the tree-based algorithm classifiers are optimized by usingthe grid search hyper-parameter optimization. From the experiments, RFhad proven to be the most effective algorithm, with the accuracyimproving from 89% to 93%.
关键词：Hyperparameter Optimization; Learning Style; Online Learning;Tree-based Algorithm