Work

A Machine Learning Approach to Predict Technology Integration Among Mathematics Teacher Educators

Year: 2015
Type: article
Abstract: This study aims to predict the willingness and proficiency of Mathematics Teacher Educators (MTEs) in integrating technology into mathematics instruction. This study employs a machine learning approach to predict the willingness and proficiency of Mathematics Teacher Educators (MTEs) in integrating technology into mathematics instruction. Secondary data from 104 MTEs were analyzed using a decision tree model to identify the most significant predictors of technology integration. The analysis revealed that familiarity with and perceived ease of use of technology were the primary determinants of MTEs’ willingness to adopt digital tools in teaching. Moreover, higher education levels and institutional support were associated with greater technological proficiency. Despite limited prior experience, many MTEs displayed a constructive attitude toward technology adoption, suggesting a readiness to engage in continuous digital learning. These findings provide actionable insights for policymakers and professional development designers in developing targeted training programs that enhance digital competence among teacher educators. Beyond its practical implications, this study contributes by showing how machine learning can extend TAM and UTAUT frameworks, revealing nonlinear relationships and offering data-driven insights into technology integration among mathematics teacher educators.
Authors: Universitas Pendidikan Indonesia, Indonesia, Churun L. Maknun, Rizky Rosjanuardi, Universitas Pendidikan Indonesia, Indonesia, Dadan Dasari, Universitas Pendidikan Indonesia, Indonesia
Language: English
Subfield: Education
Open Access status: diamond
OpenAlex ID: W7115576687
FWCI:
Cites:
Cited by: 2
Related to: 10