Leveraging Artificial Neural Networks to Predict and Enhance Student Performance in Virtual Learning Environments

Objective: This study aimed at exploring the link between sort of features in the Moodle platforms: activity design, student interaction, feature usage, adaptability, and access time and students' academic performance in the Open University Indonesia's Master of Management Education Program.Methods: A quantitative research design was adopted by employing purposive sampling in determining 250 students within the Master of Management Education Programme. They collected data using surveys, Moodle activity logs, and institutional records. Descriptive statistics, reliability tests, correlation, regression analysis, and structural equation modeling (SEM) were performed to analyze the data and determine relationships between the Moodle features and academic performance.Results: The findings showed that the five dimensions of activity design, student interaction, feature usage, adaptability, and access time were all statistically significant and positively associated with academic performance. Feature usage proved to be the greatest predictor for academic success, followed by activity design and student interaction. It also found that adaptability and access time, while important, had a smaller immediate influence on academic performance.Novelty: This study adds to the literature by using artificial neural networks (ANN) for predicting academic performance using features from the Moodle platform. It is a pioneering study that investigates multiple Moodle features, including course structure, student interaction and adaptability, and its regard to the academic performance of students in higher education, specifically in the Master of Management Education Programme.Research Implications: These findings have significant implications for online course design and teaching practices. Moodle instructors are only as good as their course activities effective course activities should create a well-structured, interactive ‘framework’ that engages students to use the features and tools available in Moodle. The study stated that It also identifies the need to enhance students' digital literacy and adaptability to fully leverage the advantages of online learning platforms. This will help the institutions to improve student engagement and academic performance by improving the learning environment in Moodle or other technology used in the education institution.

Authors

Institutions

Publication Details

Journal
Researcher Academy Innovation Data Analysis
Published
2024-12-24
DOI
https://doi.org/10.69725/raida.v1i2.162
Citations
1
Primary Topic
Online Learning and Analytics
Type
article
Field-Weighted Citation Impact
0.41
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Leveraging Artificial Neural Networks to Predict and Enhance Student Performance in Virtual Learning Environments

Retno Ryani Kusumawati
1 citations
Researcher Academy Innovation Data Analysis
Online Learning and Analytics
0.41
article

Leveraging Artificial Neural Networks to Predict and Enhance Student Performance in Virtual Learning Environments

Retno Ryani Kusumawati
article en
1 citations

Abstract

Objective: This study aimed at exploring the link between sort of features in the Moodle platforms: activity design, student interaction, feature usage, adaptability, and access time and students' academic performance in the Open University Indonesia's Master of Management Education Program.Methods: A quantitative research design was adopted by employing purposive sampling in determining 250 students within the Master of Management Education Programme. They collected data using surveys, Moodle activity logs, and institutional records. Descriptive statistics, reliability tests, correlation, regression analysis, and structural equation modeling (SEM) were performed to analyze the data and determine relationships between the Moodle features and academic performance.Results: The findings showed that the five dimensions of activity design, student interaction, feature usage, adaptability, and access time were all statistically significant and positively associated with academic performance. Feature usage proved to be the greatest predictor for academic success, followed by activity design and student interaction. It also found that adaptability and access time, while important, had a smaller immediate influence on academic performance.Novelty: This study adds to the literature by using artificial neural networks (ANN) for predicting academic performance using features from the Moodle platform. It is a pioneering study that investigates multiple Moodle features, including course structure, student interaction and adaptability, and its regard to the academic performance of students in higher education, specifically in the Master of Management Education Programme.Research Implications: These findings have significant implications for online course design and teaching practices. Moodle instructors are only as good as their course activities effective course activities should create a well-structured, interactive ‘framework’ that engages students to use the features and tools available in Moodle. The study stated that It also identifies the need to enhance students' digital literacy and adaptability to fully leverage the advantages of online learning platforms. This will help the institutions to improve student engagement and academic performance by improving the learning environment in Moodle or other technology used in the education institution.

Researcher Academy Innovation Data AnalysisVol. 1(2)
Indonesia Open University (ID)
Quality Education
Openalex Percentile: Top 24%
Online Learning and Analytics
0.41
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.