Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data
Digital data trails from disparate sources covering different aspects of student life are stored daily in most modern university campuses. However, it remains challenging to (i) combine these data to obtain a holistic view of a student, (ii) use these data to accurately predict academic performance,...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9118933/ |
id |
doaj-bbc55b3d49f64b7a977868653758d27b |
---|---|
record_format |
Article |
spelling |
doaj-bbc55b3d49f64b7a977868653758d27b2021-03-30T15:16:47ZengIEEEIEEE Access2169-35362021-01-0195453546510.1109/ACCESS.2020.30027919118933Academic Performance Prediction Based on Multisource, Multifeature Behavioral DataLiang Zhao0https://orcid.org/0000-0003-0678-489XKun Chen1Jie Song2Xiaoliang Zhu3Jianwen Sun4Brian Caulfield5https://orcid.org/0000-0003-0290-9587Brian Mac Namee6National Engineering Laboratory for Educational Big Data, National Engineering Research Center for E-learning, Central China Normal University, Wuhan, ChinaNational Engineering Laboratory for Educational Big Data, National Engineering Research Center for E-learning, Central China Normal University, Wuhan, ChinaNational Engineering Laboratory for Educational Big Data, National Engineering Research Center for E-learning, Central China Normal University, Wuhan, ChinaNational Engineering Laboratory for Educational Big Data, National Engineering Research Center for E-learning, Central China Normal University, Wuhan, ChinaNational Engineering Laboratory for Educational Big Data, National Engineering Research Center for E-learning, Central China Normal University, Wuhan, ChinaThe Insight Center for Data Analytics, University College Dublin, Dublin, IrelandThe Insight Center for Data Analytics, University College Dublin, Dublin, IrelandDigital data trails from disparate sources covering different aspects of student life are stored daily in most modern university campuses. However, it remains challenging to (i) combine these data to obtain a holistic view of a student, (ii) use these data to accurately predict academic performance, and (iii) use such predictions to promote positive student engagement with the university. To initially alleviate this problem, in this article, a model named Augmented Education (AugmentED) is proposed. In our study, (1) first, an experiment is conducted based on a real-world campus dataset of college students (N =156 ) that aggregates multisource behavioral data covering not only online and offline learning but also behaviors inside and outside of the classroom. Specifically, to gain in-depth insight into the features leading to excellent or poor performance, metrics measuring the linear and nonlinear behavioral changes (e.g., regularity and stability) of campus lifestyles are estimated; furthermore, features representing dynamic changes in temporal lifestyle patterns are extracted by the means of long short-term memory (LSTM). (2) Second, machine learning-based classification algorithms are developed to predict academic performance. (3) Finally, visualized feedback enabling students (especially at-risk students) to potentially optimize their interactions with the university and achieve a study-life balance is designed. The experiments show that the AugmentED model can predict students' academic performance with high accuracy.https://ieeexplore.ieee.org/document/9118933/Academic performance predictionbehavioral patterndigital campusmachine learning (ML)long short-term memory (LSTM) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Liang Zhao Kun Chen Jie Song Xiaoliang Zhu Jianwen Sun Brian Caulfield Brian Mac Namee |
spellingShingle |
Liang Zhao Kun Chen Jie Song Xiaoliang Zhu Jianwen Sun Brian Caulfield Brian Mac Namee Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data IEEE Access Academic performance prediction behavioral pattern digital campus machine learning (ML) long short-term memory (LSTM) |
author_facet |
Liang Zhao Kun Chen Jie Song Xiaoliang Zhu Jianwen Sun Brian Caulfield Brian Mac Namee |
author_sort |
Liang Zhao |
title |
Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data |
title_short |
Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data |
title_full |
Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data |
title_fullStr |
Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data |
title_full_unstemmed |
Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data |
title_sort |
academic performance prediction based on multisource, multifeature behavioral data |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
Digital data trails from disparate sources covering different aspects of student life are stored daily in most modern university campuses. However, it remains challenging to (i) combine these data to obtain a holistic view of a student, (ii) use these data to accurately predict academic performance, and (iii) use such predictions to promote positive student engagement with the university. To initially alleviate this problem, in this article, a model named Augmented Education (AugmentED) is proposed. In our study, (1) first, an experiment is conducted based on a real-world campus dataset of college students (N =156 ) that aggregates multisource behavioral data covering not only online and offline learning but also behaviors inside and outside of the classroom. Specifically, to gain in-depth insight into the features leading to excellent or poor performance, metrics measuring the linear and nonlinear behavioral changes (e.g., regularity and stability) of campus lifestyles are estimated; furthermore, features representing dynamic changes in temporal lifestyle patterns are extracted by the means of long short-term memory (LSTM). (2) Second, machine learning-based classification algorithms are developed to predict academic performance. (3) Finally, visualized feedback enabling students (especially at-risk students) to potentially optimize their interactions with the university and achieve a study-life balance is designed. The experiments show that the AugmentED model can predict students' academic performance with high accuracy. |
topic |
Academic performance prediction behavioral pattern digital campus machine learning (ML) long short-term memory (LSTM) |
url |
https://ieeexplore.ieee.org/document/9118933/ |
work_keys_str_mv |
AT liangzhao academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata AT kunchen academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata AT jiesong academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata AT xiaoliangzhu academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata AT jianwensun academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata AT briancaulfield academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata AT brianmacnamee academicperformancepredictionbasedonmultisourcemultifeaturebehavioraldata |
_version_ |
1724179794364465152 |