<![CDATA[The rapid integration of artificial intelligence (AI) into education has opened new possibilities for personalized learning, yet emotional engagement remains an underdeveloped dimension in hybrid learning environments. Traditional AI tutoring systems primarily focus on cognitive adaptation, often neglecting the affective aspects that influence student motivation, attention, and persistence. This study explores the use of affective computing to develop emotion-aware virtual tutors capable of recognizing and responding to learners’ emotional states in real time. The research aims to design and evaluate a hybrid AI tutoring model that integrates facial expression recognition, voice sentiment analysis, and physiological data interpretation to deliver adaptive emotional feedback. The study employed a mixed-method approach combining system prototyping, experimental testing, and learner experience evaluation. Data were collected from 120 middle and university students engaged in hybrid science courses, using emotion-recognition accuracy rates, engagement indices, and qualitative interviews as core evaluation metrics. Results showed that the emotion-aware tutor achieved an average recognition accuracy of 91.2% and improved learner engagement by 34% compared to traditional AI tutors. Students reported higher satisfaction and felt more connected to the virtual tutor, indicating that emotional responsiveness enhanced trust and motivation. The findings demonstrate that affective AI systems can humanize digital learning interactions, providing affect-sensitive feedback that complements cognitive personalization. Future research should explore ethical frameworks for emotion data privacy and expand cross-cultural models of emotional intelligence in AI tutoring.]]>
Copyrights © 2025
