Towards a wearable education: Understanding the determinants affecting students' adoption of wearable technologies using machine learning algorithms

The emergence of wearable technologies, including smartwatches, has received a considerable attention from scholars across several sectors. However, there is a scarcity of knowledge regarding the determinants affecting the adoption of these wearables in education. Therefore, this research aims to propose a theoretical research model through the integration of the theory of planned behavior (TPB) and protection motivation theory (PMT) to understand the students' behavioral intention to use smartwatches in learning activities. Through the use of machine learning classification algorithms, the proposed model has been validated using data collected via an online survey from 511 university students. The results indicated that perceived severity, perceived vulnerability, self-efficacy, response efficacy, subjective norm, attitude, and perceived behavioral control have a significant positive impact on students' behavioral intention to use smartwatches for educational purposes. Besides, response cost was found to have a significant negative effect on students' behavioral intention. The evidence from these findings provides the policy-makers in higher educational institutions with a clear vision of the most effective policies and best practices to enhance the capacity and potential use of these wearables in educational activities. The theoretical contributions and practical implications were also discussed.