Modeling E-Behaviour, Personality and Academic Performance with Machine Learning

The analysis of student performance involves data modelling that enables the formulation of hypotheses and insights about student behaviour and personality. We extract online behaviours as proxies to Extraversion and Conscientiousness, which have been proven to correlate with academic performance. T...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Serepu Bill-William Seota, Richard Klein, Terence van Zyl
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/64355bc4eab74c7ab1cacb315ceb7599
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:64355bc4eab74c7ab1cacb315ceb7599
record_format dspace
spelling oai:doaj.org-article:64355bc4eab74c7ab1cacb315ceb75992021-11-25T16:31:12ZModeling E-Behaviour, Personality and Academic Performance with Machine Learning10.3390/app1122105462076-3417https://doaj.org/article/64355bc4eab74c7ab1cacb315ceb75992021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10546https://doaj.org/toc/2076-3417The analysis of student performance involves data modelling that enables the formulation of hypotheses and insights about student behaviour and personality. We extract online behaviours as proxies to Extraversion and Conscientiousness, which have been proven to correlate with academic performance. The proxies of personalities we obtain yield significant (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>p</mi><mo><</mo><mn>0.05</mn></mrow></semantics></math></inline-formula>) population correlation coefficients for traits against grade—<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.846</mn></mrow></semantics></math></inline-formula> for Extraversion and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.319</mn></mrow></semantics></math></inline-formula> for Conscientiousness. Furthermore, we demonstrate that a student’s e-behaviour and personality can be used with deep learning (LSTM) to predict and forecast whether a student is at risk of failing the year. Machine learning procedures followed in this report provide a methodology to timeously identify students who are likely to become at risk of poor academic performance. Using engineered online behaviour and personality features, we obtain a classification accuracy (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>κ</mi></semantics></math></inline-formula>) of students at risk of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.51</mn></mrow></semantics></math></inline-formula>. Lastly, we show that we can design an intervention process using machine learning that supplements the existing performance analysis and intervention methods. The methodology presented in this article provides metrics that measure the factors that affect student performance and complement the existing performance evaluation and intervention systems in education.Serepu Bill-William SeotaRichard KleinTerence van ZylMDPI AGarticlee-behaviourbig five personalitystudent performanceTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10546, p 10546 (2021)
institution DOAJ
collection DOAJ
language EN
topic e-behaviour
big five personality
student performance
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle e-behaviour
big five personality
student performance
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
Serepu Bill-William Seota
Richard Klein
Terence van Zyl
Modeling E-Behaviour, Personality and Academic Performance with Machine Learning
description The analysis of student performance involves data modelling that enables the formulation of hypotheses and insights about student behaviour and personality. We extract online behaviours as proxies to Extraversion and Conscientiousness, which have been proven to correlate with academic performance. The proxies of personalities we obtain yield significant (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>p</mi><mo><</mo><mn>0.05</mn></mrow></semantics></math></inline-formula>) population correlation coefficients for traits against grade—<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.846</mn></mrow></semantics></math></inline-formula> for Extraversion and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.319</mn></mrow></semantics></math></inline-formula> for Conscientiousness. Furthermore, we demonstrate that a student’s e-behaviour and personality can be used with deep learning (LSTM) to predict and forecast whether a student is at risk of failing the year. Machine learning procedures followed in this report provide a methodology to timeously identify students who are likely to become at risk of poor academic performance. Using engineered online behaviour and personality features, we obtain a classification accuracy (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi>κ</mi></semantics></math></inline-formula>) of students at risk of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.51</mn></mrow></semantics></math></inline-formula>. Lastly, we show that we can design an intervention process using machine learning that supplements the existing performance analysis and intervention methods. The methodology presented in this article provides metrics that measure the factors that affect student performance and complement the existing performance evaluation and intervention systems in education.
format article
author Serepu Bill-William Seota
Richard Klein
Terence van Zyl
author_facet Serepu Bill-William Seota
Richard Klein
Terence van Zyl
author_sort Serepu Bill-William Seota
title Modeling E-Behaviour, Personality and Academic Performance with Machine Learning
title_short Modeling E-Behaviour, Personality and Academic Performance with Machine Learning
title_full Modeling E-Behaviour, Personality and Academic Performance with Machine Learning
title_fullStr Modeling E-Behaviour, Personality and Academic Performance with Machine Learning
title_full_unstemmed Modeling E-Behaviour, Personality and Academic Performance with Machine Learning
title_sort modeling e-behaviour, personality and academic performance with machine learning
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/64355bc4eab74c7ab1cacb315ceb7599
work_keys_str_mv AT serepubillwilliamseota modelingebehaviourpersonalityandacademicperformancewithmachinelearning
AT richardklein modelingebehaviourpersonalityandacademicperformancewithmachinelearning
AT terencevanzyl modelingebehaviourpersonalityandacademicperformancewithmachinelearning
_version_ 1718413139104497664