Predicting teacher resilience by using artificial neural networks: influence of burnout and stress by COVID-19.

Abstract

Background: Resilience in teachers allows them to face difficult situations to recover from adversity and there are gender differences. Likewise, artificial intelligence and the techniques associated with it have proven to be very useful in predicting educational variables and studying the interconnection between them after COVID-19. That said, the general objective of this research was to predict the levels of resilience in secondary school teachers through the design of an artificial neural network (ANN). Method: The Brief Resilient Coping Scale, the Maslach Burnout Inventory and the COVID-19 Stress Questionnaire were administered to 401 secondary school teachers (70.6% female) from schools in southeastern Spain, with a mean age of 44.36 years (SD = 9.38). Results: Differences were found in the configuration of the predictive models of resilience between male and female teachers, with the independent variables contrib-uting to different degrees depending on gender. Conclusions: It is highlighted the usefulness of ANNs in the educational setting and the need to design more adjusted programs.