Structural equation model (SEM)-neural network (NN) model for predicting quality determinants of e-learning management systems

Sujeet Kumar Sharma, Avinash Gaur, Venkataramanaiah Saddikuti, Ashish Rastogi

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

The success of e-learning management systems (e-LMSs) such as MOODLE depends on the usage of students as well as instructor acceptance in a virtual learning environment. E-Learning enables instructors to access educational resources to support traditional classroom teaching. This paper attempts to develop a model to understand and predict the effect of individual characteristics (technology experience [TE] and personal innovativeness [PI]) and e-LMS quality determinants (system quality [SYS-Q], information quality, and service quality) on the continuous use of e-LMS by instructors, which is critical to its success. A total of 219 instructors using MOODLE responded to the survey. The structural equation model (SEM) was employed to test the proposed research model. The SEM results showed that SYS-Q, PI, service quality, and TE have a statistically significant influence on continuous usage of e-LMS by instructors. Furthermore, all determinants of the research model were given as input to an NN model to overcome the simplistic nature of the SEM model. The NN model results showed that service quality is the most important predictor of e-learning acceptance followed by SYS-Q, PI, information quality, and TE. This paper attempts to develop a causal and predictive statistical model for predicting instructor e-LMS acceptance.

Original languageEnglish
Pages (from-to)1053-1066
Number of pages14
JournalBehaviour and Information Technology
Volume36
Issue number10
DOIs
Publication statusPublished - Oct 3 2017

Fingerprint

Neural Networks (Computer)
Structural Models
structural model
neural network
electronic learning
Learning
determinants
Neural networks
instructor
management
acceptance
Technology
personal services
Information Services
Structural Equation Model
Electronic Learning
Neural Network Model
E-learning
experience
Statistical Models

Keywords

  • E-learning
  • LMS
  • MOODLE
  • Oman
  • personal innovation
  • service quality
  • technology adoption

ASJC Scopus subject areas

  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)
  • Social Sciences(all)
  • Human-Computer Interaction

Cite this

Structural equation model (SEM)-neural network (NN) model for predicting quality determinants of e-learning management systems. / Sharma, Sujeet Kumar; Gaur, Avinash; Saddikuti, Venkataramanaiah; Rastogi, Ashish.

In: Behaviour and Information Technology, Vol. 36, No. 10, 03.10.2017, p. 1053-1066.

Research output: Contribution to journalArticle

@article{88bc35749b9a40f2853c1dc16c4159f8,
title = "Structural equation model (SEM)-neural network (NN) model for predicting quality determinants of e-learning management systems",
abstract = "The success of e-learning management systems (e-LMSs) such as MOODLE depends on the usage of students as well as instructor acceptance in a virtual learning environment. E-Learning enables instructors to access educational resources to support traditional classroom teaching. This paper attempts to develop a model to understand and predict the effect of individual characteristics (technology experience [TE] and personal innovativeness [PI]) and e-LMS quality determinants (system quality [SYS-Q], information quality, and service quality) on the continuous use of e-LMS by instructors, which is critical to its success. A total of 219 instructors using MOODLE responded to the survey. The structural equation model (SEM) was employed to test the proposed research model. The SEM results showed that SYS-Q, PI, service quality, and TE have a statistically significant influence on continuous usage of e-LMS by instructors. Furthermore, all determinants of the research model were given as input to an NN model to overcome the simplistic nature of the SEM model. The NN model results showed that service quality is the most important predictor of e-learning acceptance followed by SYS-Q, PI, information quality, and TE. This paper attempts to develop a causal and predictive statistical model for predicting instructor e-LMS acceptance.",
keywords = "E-learning, LMS, MOODLE, Oman, personal innovation, service quality, technology adoption",
author = "Sharma, {Sujeet Kumar} and Avinash Gaur and Venkataramanaiah Saddikuti and Ashish Rastogi",
year = "2017",
month = "10",
day = "3",
doi = "10.1080/0144929X.2017.1340973",
language = "English",
volume = "36",
pages = "1053--1066",
journal = "Behaviour and Information Technology",
issn = "0144-929X",
publisher = "Taylor and Francis Ltd.",
number = "10",

}

TY - JOUR

T1 - Structural equation model (SEM)-neural network (NN) model for predicting quality determinants of e-learning management systems

AU - Sharma, Sujeet Kumar

AU - Gaur, Avinash

AU - Saddikuti, Venkataramanaiah

AU - Rastogi, Ashish

PY - 2017/10/3

Y1 - 2017/10/3

N2 - The success of e-learning management systems (e-LMSs) such as MOODLE depends on the usage of students as well as instructor acceptance in a virtual learning environment. E-Learning enables instructors to access educational resources to support traditional classroom teaching. This paper attempts to develop a model to understand and predict the effect of individual characteristics (technology experience [TE] and personal innovativeness [PI]) and e-LMS quality determinants (system quality [SYS-Q], information quality, and service quality) on the continuous use of e-LMS by instructors, which is critical to its success. A total of 219 instructors using MOODLE responded to the survey. The structural equation model (SEM) was employed to test the proposed research model. The SEM results showed that SYS-Q, PI, service quality, and TE have a statistically significant influence on continuous usage of e-LMS by instructors. Furthermore, all determinants of the research model were given as input to an NN model to overcome the simplistic nature of the SEM model. The NN model results showed that service quality is the most important predictor of e-learning acceptance followed by SYS-Q, PI, information quality, and TE. This paper attempts to develop a causal and predictive statistical model for predicting instructor e-LMS acceptance.

AB - The success of e-learning management systems (e-LMSs) such as MOODLE depends on the usage of students as well as instructor acceptance in a virtual learning environment. E-Learning enables instructors to access educational resources to support traditional classroom teaching. This paper attempts to develop a model to understand and predict the effect of individual characteristics (technology experience [TE] and personal innovativeness [PI]) and e-LMS quality determinants (system quality [SYS-Q], information quality, and service quality) on the continuous use of e-LMS by instructors, which is critical to its success. A total of 219 instructors using MOODLE responded to the survey. The structural equation model (SEM) was employed to test the proposed research model. The SEM results showed that SYS-Q, PI, service quality, and TE have a statistically significant influence on continuous usage of e-LMS by instructors. Furthermore, all determinants of the research model were given as input to an NN model to overcome the simplistic nature of the SEM model. The NN model results showed that service quality is the most important predictor of e-learning acceptance followed by SYS-Q, PI, information quality, and TE. This paper attempts to develop a causal and predictive statistical model for predicting instructor e-LMS acceptance.

KW - E-learning

KW - LMS

KW - MOODLE

KW - Oman

KW - personal innovation

KW - service quality

KW - technology adoption

UR - http://www.scopus.com/inward/record.url?scp=85021114115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021114115&partnerID=8YFLogxK

U2 - 10.1080/0144929X.2017.1340973

DO - 10.1080/0144929X.2017.1340973

M3 - Article

VL - 36

SP - 1053

EP - 1066

JO - Behaviour and Information Technology

JF - Behaviour and Information Technology

SN - 0144-929X

IS - 10

ER -