View in EDS

Improving Learning Style Prediction using Tree-based Algorithm with Hyperparameter Optimization.

Saved in:
Bibliographic Details
Title: Improving Learning Style Prediction using Tree-based Algorithm with Hyperparameter Optimization.
Authors: Shamsudin, Haziqah, Yusof, Umi Kalsom, Sabudin, Maziani
Source: International Journal of Advances in Soft Computing & Its Applications; Apr2020, Vol. 12 Issue 1, p65-80, 16p
Subject Terms: COGNITIVE styles, FORECASTING, PROCESS optimization, INFORMATION commons, DECISION trees, RANDOM forest algorithms
Abstract: Learning style of specific users in an online learning system is determined based on their interaction and behavior towards the system. The most common online learning theory used in determining the learning style is the Felder-Silvermans Theory. Many researchers have proposed machine learning algorithms to establish learning style by using log file attributes. However, they did not optimize the parameters selections which also contribute to low performance matrices. In this paper, tree-based algorithm is being used to detect the learning style of the user. The tree-based algorithms used in this paper are the Decision Tree (CART), Random Forest (RF), and Extreme Gradient Boosting (Xgb). In order to optimize the results of the performance matrices, the parameters of the tree-based algorithm classifiers are optimized by using the grid search hyper-parameter optimization. From the experiments, RF had proven to be the most effective algorithm, with the accuracy improving from 89% to 93%. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Advances in Soft Computing & Its Applications is the property of Al-Zaytoonah University of Jordan, Faculty of Science & Information Technology and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:Learning style of specific users in an online learning system is determined based on their interaction and behavior towards the system. The most common online learning theory used in determining the learning style is the Felder-Silvermans Theory. Many researchers have proposed machine learning algorithms to establish learning style by using log file attributes. However, they did not optimize the parameters selections which also contribute to low performance matrices. In this paper, tree-based algorithm is being used to detect the learning style of the user. The tree-based algorithms used in this paper are the Decision Tree (CART), Random Forest (RF), and Extreme Gradient Boosting (Xgb). In order to optimize the results of the performance matrices, the parameters of the tree-based algorithm classifiers are optimized by using the grid search hyper-parameter optimization. From the experiments, RF had proven to be the most effective algorithm, with the accuracy improving from 89% to 93%. [ABSTRACT FROM AUTHOR]
ISSN:27101274