Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine
In many academic fields, predicting student academic success using data mining techniques has long been a major research issue. Monitoring students in higher education institutions (HEIs) and having the ability to predict student performance is important to improve academic quality. The objective of...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-03-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/5/3267 |
_version_ | 1797615717428756480 |
---|---|
author | Nur Izzati Mohd Talib Nazatul Aini Abd Majid Shahnorbanun Sahran |
author_facet | Nur Izzati Mohd Talib Nazatul Aini Abd Majid Shahnorbanun Sahran |
author_sort | Nur Izzati Mohd Talib |
collection | DOAJ |
description | In many academic fields, predicting student academic success using data mining techniques has long been a major research issue. Monitoring students in higher education institutions (HEIs) and having the ability to predict student performance is important to improve academic quality. The objective of the study is to (1) identify features that form clusters that have holistic characteristics and (2) develop and validate a prediction model for each of the clusters to predict student performance holistically. For this study, both classification and clustering methods will be used using Support Vector Machine (SVM) and K-means clustering. Three clusters were identified using K-means clustering. Based on the learning program outcome feature, there are primarily three types of students: low, average, and high performance. The prediction model with the new labels obtained from the clusters also gained higher accuracy when compared to the student dataset with labels using their semester grade. |
first_indexed | 2024-03-11T07:29:39Z |
format | Article |
id | doaj.art-4fb0e90f538743fe92efbc72027f8338 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-11T07:29:39Z |
publishDate | 2023-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-4fb0e90f538743fe92efbc72027f83382023-11-17T07:21:31ZengMDPI AGApplied Sciences2076-34172023-03-01135326710.3390/app13053267Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector MachineNur Izzati Mohd Talib0Nazatul Aini Abd Majid1Shahnorbanun Sahran2Center for Artificial Intelligence Technology, Faculty of Information Science & Technology, Universiti Kebangsaan Malaysia, Bangi 43600, MalaysiaCenter for Artificial Intelligence Technology, Faculty of Information Science & Technology, Universiti Kebangsaan Malaysia, Bangi 43600, MalaysiaCenter for Artificial Intelligence Technology, Faculty of Information Science & Technology, Universiti Kebangsaan Malaysia, Bangi 43600, MalaysiaIn many academic fields, predicting student academic success using data mining techniques has long been a major research issue. Monitoring students in higher education institutions (HEIs) and having the ability to predict student performance is important to improve academic quality. The objective of the study is to (1) identify features that form clusters that have holistic characteristics and (2) develop and validate a prediction model for each of the clusters to predict student performance holistically. For this study, both classification and clustering methods will be used using Support Vector Machine (SVM) and K-means clustering. Three clusters were identified using K-means clustering. Based on the learning program outcome feature, there are primarily three types of students: low, average, and high performance. The prediction model with the new labels obtained from the clusters also gained higher accuracy when compared to the student dataset with labels using their semester grade.https://www.mdpi.com/2076-3417/13/5/3267student academic performanceidentification of student behavioral patternhigher educationmachine learningsupport vector machinek-means clustering |
spellingShingle | Nur Izzati Mohd Talib Nazatul Aini Abd Majid Shahnorbanun Sahran Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine Applied Sciences student academic performance identification of student behavioral pattern higher education machine learning support vector machine k-means clustering |
title | Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine |
title_full | Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine |
title_fullStr | Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine |
title_full_unstemmed | Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine |
title_short | Identification of Student Behavioral Patterns in Higher Education Using K-Means Clustering and Support Vector Machine |
title_sort | identification of student behavioral patterns in higher education using k means clustering and support vector machine |
topic | student academic performance identification of student behavioral pattern higher education machine learning support vector machine k-means clustering |
url | https://www.mdpi.com/2076-3417/13/5/3267 |
work_keys_str_mv | AT nurizzatimohdtalib identificationofstudentbehavioralpatternsinhighereducationusingkmeansclusteringandsupportvectormachine AT nazatulainiabdmajid identificationofstudentbehavioralpatternsinhighereducationusingkmeansclusteringandsupportvectormachine AT shahnorbanunsahran identificationofstudentbehavioralpatternsinhighereducationusingkmeansclusteringandsupportvectormachine |