Emotional Intelligence Meets Artificial Intelligence Affective Computing and Student Well-Being Online Classrooms

Abstract

This work was on the use of emotional intelligence and affective computing systems to predict well-being, engagement in their studies, and drop-out in online educational settings. The research design was quantitative, correlational, and predictive, and the data were collected in the context of 250 university students in both the public and private educational institutions of Pakistan by using simple random samples. To test 3 hypotheses, descriptive statistics, Pearson correlation, simple linear regression, and multiple linear regression were performed. The findings indicated a significant positive correlation of strong coefficient between the emotional intelligence of students and academic well-being, and the assumption that emotional competencies are also important in the management of stress and motivation in online learning has been justified. Also, the affective computing systems were identified to be significant predictors of the academic involvement of the students, so the emission-sensitive AI tools seemed to positively affect participation by anticipating emotional misery and prompting on-demand, adaptive assistance. The multiple regression analysis was able to prove the hypothesis true that both emotionally intelligent AI systems and the emotional well-being of students contributed significantly to dropout risks and explained a significant portion of the varieties in the rates of academic retention. This research backs such suggestions as including the concepts of affective computing and emotional intelligence in online educational systems to foster psychological robustness and academic achievement.