Impact of Technostress on Academic Performance and Student Learning Burnout and Decision Making using Fuzzy concept and Machine Learning Techniques
Abstract
The speed at which digital technologies have integrated within the educational field has caused a notable change in the learning environment while at the same time introducing technostress amongst students. It is a study to investigate the effect of technostress on academic performance, learning burnout, and decision-making efficiency using a hybrid framework using fuzzy logic concepts and machine learning techniques. The key dimensions of technostress such as techno-overload, techno-invasion, techno-complexity, techno-insecurity, techno-uncertainty as well as the indicators of learning burnout, academic attributes are analyzed. Fuzzy logic is used for the management of the uncertainty and subjectivity in understanding the psychological data using linguistic modeling and Rule-based inference, whereas Machine learning algorithms such as Support Vector Machines, Random Forests Machines, Decision Trees, Neural networks, etc., capture the non-linear relationship between the data. Experimental results show that the combination of fuzzy outputs to boost the prediction results provides accuracy and the interpretability of the results compared to the standalone models. The results show an extremely negative impact of important levels of technostress influence on performance at work (academic) and decision-making efficiency mediated by an increased state of learning burnout. The proposed approach offers an effective decision support mechanism for the early identification of technostress affected students and data driven academic interventions.