학술논문

Uncovering the Critical Drivers of Blockchain Sustainability in Higher Education Using a Deep Learning-Based Hybrid SEM-ANN Approach
Document Type
Periodical
Source
IEEE Transactions on Engineering Management IEEE Trans. Eng. Manage. Engineering Management, IEEE Transactions on. 71:8192-8208 2024
Subject
Engineering Profession
Blockchains
Education
Sustainable development
Mathematical models
Informatics
Fraud
Supply chain management
Blockchain
deep learning
drivers
higher education
structural equation modeling and artificial neural network (SEM-ANN)
sustainability
Language
ISSN
0018-9391
1558-0040
Abstract
The increasing popularity of blockchain technology has led to its adoption in various sectors, including higher education. However, the sustainability of blockchain in higher education is yet to be fully understood. Therefore, this research examines the determinants affecting blockchain sustainability by developing a theoretical model that integrates the protection motivation theory and expectation confirmation model. Based on 374 valid responses collected from university students, the proposed model is evaluated through a deep learning-based hybrid structural equation modeling (SEM) and artificial neural network approach. The partial least squares-SEM results confirmed most of the hypotheses in the proposed model. The sensitivity analysis outcomes discovered that users’ satisfaction is the most important factor affecting blockchain sustainability, with 100% normalized importance, followed by perceived usefulness (58.8%), perceived severity (12.1%), and response costs (9.2%). The findings of this research provide valuable insights for higher education institutions and other stakeholders looking to sustain the use of blockchain technology.