A Hybrid Machine Learning Framework for Predicting Students’ Performance in Virtual Learning Environment

Evangelista, Edmund

doi:10.3991/ijet.v16i24.26151

Cited by 23 publications

(12 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This platform improves the skills of students in digital learning. Literature reviews have also highlighted the immersion of diverse students from different domains in virtual reality platforms, including Evangelista ( 2021 ), who reported on medical students, and Canessa and Tenze (2021 ), who developed a new medium, OpenEyA, based on YouTube. This platform permits archiving and sharing traditional of courses for students of mathematics and physics without human interference or expensive management.…”

Section: Related Workmentioning

confidence: 99%

Development of an intelligent system based on metaverse learning for students with disabilities

2022

View full text Add to dashboard Cite

Due to the coronavirus-2019 pandemic, people have had to work and study using the Internet such that the strengthened metaverse has become a part of the lives of people worldwide. The advent of technology linking the real and virtual worlds has facilitated the transmission of spatial audio and haptics to allow the metaverse to offer multisensory experiences in diverse fields, especially in teaching. The main idea of the proposed project is the development of a simple intelligent system for meta-learning. The suggested system should be self-configurable according to the different users of the metaverse. We aimed to design and create a virtual learning environment using Open Simulator based on a 3D virtual environment and simulation of the real-world environment. We then connected this environment to a learning management system (Moodle) through technology for 3D virtual environments (Sloodle) to allow the management of students, especially those with different abilities, and followed up on their activities, tests, and exams. This environment also has the advantage of storing educational content. We evaluated the performance of the Open Simulator in both standalone and grid modes based on the login times. The result showed times the standalone and grid modes of 12 s and 16 s, which demonstrated the robustness of the proposed platform. We also tested the system on 50 disabled learners, according to the t-test of independent samples. A test was conducted in the mathematics course, in which the students were divided into two equal groups (n = 25 each) to take the test traditionally and using the chair test tool, which is one of the most important tools of the Sloodle technology. According to the results, the null hypothesis was rejected, and we accepted the alternative hypothesis that demonstrated a difference in achievement between the two groups.

show abstract

Section: Related Workmentioning

confidence: 99%

Development of an intelligent system based on metaverse learning for students with disabilities

2022

View full text Add to dashboard Cite

show abstract

“…A feature selection technique, also known as evaluators, determined the best predictors or attributes of the training dataset highly correlated to the target class [35]. This study utilized info gain and chi-squared feature selection techniques to determine the best features associated with the target class (final grade).…”

Section: Feature Selection Techniquesmentioning

confidence: 99%

“…The proposed model used the top-ranked features identified by the evaluators. To save some space but still be able to visualize the original dataset, you may opt to view the complete 32 features here [35].…”

Section: Top Features Selectedmentioning

confidence: 99%

An approach for improved students’ performance prediction using homogeneous and heterogeneous ensemble methods

Evangelista

2022

IJECE

Self Cite

View full text Add to dashboard Cite

<span lang="EN-US">Web-based learning technologies of educational institutions store a massive amount of interaction data which can be helpful to predict students’ performance through the aid of machine learning algorithms. With this, various researchers focused on studying ensemble learning methods as it is known to improve the predictive accuracy of traditional classification algorithms. This study proposed an approach for enhancing the performance prediction of different single classification algorithms by using them as base classifiers of homogeneous ensembles (bagging and boosting) and heterogeneous ensembles (voting and stacking). The model utilized various single classifiers such as multilayer perceptron or neural networks (NN), random forest (RF), naïve Bayes (NB), J48, JRip, OneR, logistic regression (LR), k-nearest neighbor (KNN), and support vector machine (SVM) to determine the base classifiers of the ensembles. In addition, the study made use of the University of California Irvine (UCI) open-access student dataset to predict students’ performance. The comparative analysis of the model’s accuracy showed that the best-performing single classifier’s accuracy increased further from 93.10% to 93.68% when used as a base classifier of a voting ensemble method. Moreover, results in this study showed that voting heterogeneous ensemble performed slightly better than bagging and boosting homogeneous ensemble methods.</span>

show abstract

“…(2022) explored how deep learning along with meta-learning was utilised to design and build a model that optimised itself for student performance prediction based on their activity within the VLE and found that course message board activity, interaction with course content and online quiz performance were features that contributed to predicting student performance. Moreover, Evangelista (2021) experimented with various machine learning classification methods to assess the most accurate model for predicting student performance and found that ensemble methods had a higher accuracy compared to single classification algorithms and that the performance of students in online assessments and quizzes, along with their midterm grades, were the best features for predicting individual student performance. Jo et al.…”

Section: Introductionmentioning

confidence: 99%

Prediction of students’ performance in online learning using supervised machine learning

Khor,

Darshan

2024

IJILT

View full text Add to dashboard Cite

PurposeThis study leverages social network analysis (SNA) to visualise the way students interacted with online resources and uses the data obtained from SNA as features for supervised machine learning algorithms to predict whether a student will successfully complete a course.Design/methodology/approachThe exploration and visualisation of the data were first carried out to gain a better understanding of the students, the course(s) each student was enrolled in and each course’s virtual learning resources. Following this, the construction of the social network graphs was performed to depict how each student behaved online before the degree centralities were computed for each of the nodes in a social network graph. Data pre-processing to assign labels based on the final result a student obtained in a course was then performed before we trained and tested models to predict which students did or did not graduate.FindingsThe study’s findings demonstrate that the constructed predictive model has good performance, as shown by the accuracy, precision, recall and f-measure metrics. The outcomes also showed that students’ use of online resources is a crucial element that influences how well they perform in their academics.Originality/valueThe similarity index is as low as 9%.

show abstract

A Hybrid Machine Learning Framework for Predicting Students’ Performance in Virtual Learning Environment

Cited by 23 publications

References 45 publications

Development of an intelligent system based on metaverse learning for students with disabilities

Development of an intelligent system based on metaverse learning for students with disabilities

An approach for improved students’ performance prediction using homogeneous and heterogeneous ensemble methods

Prediction of students’ performance in online learning using supervised machine learning

Contact Info

Product

Resources

About