Digital transformation in higher vocational education has influenced students’ processes of acquiring, engaging with, and applying digital knowledge. Existing assessment methods often prove inadequate for evaluating the complexity and dynamic nature of digital learners’ behaviours. The main purpose of the present study is to develop a robust intelligent assessment system. The cross-sectional assessment framework will apply exploratory and predictive data analyses to identify the interrelationships and complexity Technological Self-Efficacy (TSE), Learning Motivation (LM), Institutional Support (IS), Digital Collaboration Competence (DCC), and intelligent assessment use. During the data collection process, a technical cross-sectional, quantitative design was employed using a sample of 300 students from three different higher vocational institutions. The data were analysed through Exploratory Factor Analysis (EFA) to test latent constructs and utilized Random Forest Regression (RFR) to predict the Digital Literacy Enhancement (DLE) score. The findings suggest that TSE and Learning Motivation (LM) are the significantly associated with of digital literacy and that IS served as a moderator and DCC a mediator. The Random Forest model had good predictive validity (R 2 = 0.761), thus supporting model validity. The research findings suggest appropriate assessment and institutional support are positively associated with higher levels of students’ electronic literacy. In particular, institutions can use adaptive analytics and predictive modelling to not only understand students’ behaviours, but also to seek to create a deeper digital engagement, as well as create a habit of engagement with skills during the digital transformation.
Li et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: