Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model

A significant problem in Massive Open Online Courses (MOOCs) is the high rate of student dropout in these courses. An effective student dropout prediction model of MOOC courses can identify the factors responsible and provide insight on how to initiate interventions to increase student success in a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sheran Dass, Kevin Gary, James Cunningham
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	prediction dropout MOOC random forest AUC ROC Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/0f84ee38ea5e4165935ee7d901116b3e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:0f84ee38ea5e4165935ee7d901116b3e
record_format	dspace
spelling	oai:doaj.org-article:0f84ee38ea5e4165935ee7d901116b3e2021-11-25T17:58:39ZPredicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model10.3390/info121104762078-2489https://doaj.org/article/0f84ee38ea5e4165935ee7d901116b3e2021-11-01T00:00:00Zhttps://www.mdpi.com/2078-2489/12/11/476https://doaj.org/toc/2078-2489A significant problem in Massive Open Online Courses (MOOCs) is the high rate of student dropout in these courses. An effective student dropout prediction model of MOOC courses can identify the factors responsible and provide insight on how to initiate interventions to increase student success in a MOOC. Different features and various approaches are available for the prediction of student dropout in MOOC courses. In this paper, the data derived from a self-paced math course, College Algebra and Problem Solving, offered on the MOOC platform Open edX partnering with Arizona State University (ASU) from 2016 to 2020 is considered. This paper presents a model to predict the dropout of students from a MOOC course given a set of features engineered from student daily learning progress. The Random Forest Model technique in Machine Learning (ML) is used in the prediction and is evaluated using validation metrics including accuracy, precision, recall, F1-score, Area Under the Curve (AUC), and Receiver Operating Characteristic (ROC) curve. The model developed can predict the dropout or continuation of students on any given day in the MOOC course with an accuracy of 87.5%, AUC of 94.5%, precision of 88%, recall of 87.5%, and F1-score of 87.5%, respectively. The contributing features and interactions were explained using Shapely values for the prediction of the model.Sheran DassKevin GaryJames CunninghamMDPI AGarticlepredictiondropoutMOOCrandom forestAUCROCInformation technologyT58.5-58.64ENInformation, Vol 12, Iss 476, p 476 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	prediction dropout MOOC random forest AUC ROC Information technology T58.5-58.64
spellingShingle	prediction dropout MOOC random forest AUC ROC Information technology T58.5-58.64 Sheran Dass Kevin Gary James Cunningham Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model
description	A significant problem in Massive Open Online Courses (MOOCs) is the high rate of student dropout in these courses. An effective student dropout prediction model of MOOC courses can identify the factors responsible and provide insight on how to initiate interventions to increase student success in a MOOC. Different features and various approaches are available for the prediction of student dropout in MOOC courses. In this paper, the data derived from a self-paced math course, College Algebra and Problem Solving, offered on the MOOC platform Open edX partnering with Arizona State University (ASU) from 2016 to 2020 is considered. This paper presents a model to predict the dropout of students from a MOOC course given a set of features engineered from student daily learning progress. The Random Forest Model technique in Machine Learning (ML) is used in the prediction and is evaluated using validation metrics including accuracy, precision, recall, F1-score, Area Under the Curve (AUC), and Receiver Operating Characteristic (ROC) curve. The model developed can predict the dropout or continuation of students on any given day in the MOOC course with an accuracy of 87.5%, AUC of 94.5%, precision of 88%, recall of 87.5%, and F1-score of 87.5%, respectively. The contributing features and interactions were explained using Shapely values for the prediction of the model.
format	article
author	Sheran Dass Kevin Gary James Cunningham
author_facet	Sheran Dass Kevin Gary James Cunningham
author_sort	Sheran Dass
title	Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model
title_short	Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model
title_full	Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model
title_fullStr	Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model
title_full_unstemmed	Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model
title_sort	predicting student dropout in self-paced mooc course using random forest model
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/0f84ee38ea5e4165935ee7d901116b3e
work_keys_str_mv	AT sherandass predictingstudentdropoutinselfpacedmooccourseusingrandomforestmodel AT kevingary predictingstudentdropoutinselfpacedmooccourseusingrandomforestmodel AT jamescunningham predictingstudentdropoutinselfpacedmooccourseusingrandomforestmodel
_version_	1718411723957862400

Predicting Student Dropout in Self-Paced MOOC Course Using Random Forest Model

Ejemplares similares