Using machine learning algorithms to examine the impact of technostress creators on student learning burnout and perceived academic performance

Several studies have been conducted on the relationship between technostress creators and burnout in employees of business organizations. However, there is limited literature on the impact of technostress creators on students’ burnout and academic performance in Higher Educational Institutions (HEIs). This study aims to address this gap by examining the relationship between individual technostress creators, students’ learning burnout, and academic performance in an HEI. To achieve this, a new research model was proposed using constructs based on technostress creators and learning burnout to predict students’ academic performance. Data was collected from 371 students across various faculties and academic levels of Koforidua Technical University (KTU), Ghana, using an online questionnaire. The study employed the partial least square-structural equation model (PLS-SEM) method to evaluate the reliability and validity of the proposed research model. Machine learning algorithms were used to examine the relationships between individual technostress creators, students’ learning burnout, and perceived academic performance. The findings of the study suggest that techno-overload (TO), techno-uncertainty (TU), techno-invasion (TN), techno-complexity (TC), and techno-insecurity (TI) predict students’ learning burnout. Moreover, it was established that students’ learning burnout predicted perceived academic performance. The study’s results offer insights to both course instructors and HEI management on effective ways to support students in managing technostress creators.