Predicting Student Performance in Higher Educational Institutions Using Video Learning Analytics and Data Mining Techniques

Technology and innovation empower higher educational institutions (HEI) to use different types of learning systems—video learning is one such system. Analyzing the footprints left behind from these online interactions is useful for understanding the effectiveness of this kind of learning. Video-base...

Full description

Saved in:
Bibliographic Details
Published in:Applied sciences Vol. 10; no. 11; p. 3894
Main Authors: Hasan, Raza, Palaniappan, Sellappan, Mahmood, Salman, Abbas, Ali, Sarker, Kamal Uddin, Sattar, Mian Usman
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.06.2020
Subjects:
Academic achievement
Analysis
Artificial intelligence
Blended learning
classification algorithms
Data mining
data preprocessing
data transformation
Distance learning
Educational technology
Flipped classroom
Forecasts and trends
Higher education
Learning management systems
Literature reviews
Malaysia
Methods
Online instruction
Online tutorials
Public speaking
Researchers
student academic performance
Students
Studies
Success
Teachers
Technology application
Universities and colleges
video learning analytics
Video tapes in education
Malaysia
ISSN:2076-3417, 2076-3417
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Technology and innovation empower higher educational institutions (HEI) to use different types of learning systems—video learning is one such system. Analyzing the footprints left behind from these online interactions is useful for understanding the effectiveness of this kind of learning. Video-based learning with flipped teaching can help improve student’s academic performance. This study was carried out with 772 examples of students registered in e-commerce and e-commerce technologies modules at an HEI. The study aimed to predict student’s overall performance at the end of the semester using video learning analytics and data mining techniques. Data from the student information system, learning management system and mobile applications were analyzed using eight different classification algorithms. Furthermore, data transformation and preprocessing techniques were carried out to reduce the features. Moreover, genetic search and principle component analysis were carried out to further reduce the features. Additionally, the CN2 Rule Inducer and multivariate projection can be used to assist faculty in interpreting the rules to gain insights into student interactions. The results showed that Random Forest accurately predicted successful students at the end of the class with an accuracy of 88.3% with an equal width and information gain ratio.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2076-3417
2076-3417
DOI:10.3390/app10113894