Smart Tutoring: Subject Assessor with Targeted Tutor Matching and Real-Time Emotion Engagement Analysis

This research examines the evolution and deployment of ‘smart tutoring’, which is an intelligent education and learning system introducing real-time emotion recognition and tutor matching to improve learning organization. This research has far-reaching consequences offering a workable and scalable strategy that could deal with varying issues of learners in different educational settings. The focus on the instruction methods as well as student motivation within the context of this study further illustrates the current trends in educational systems towards individual learning where personalization is sought after. It stresses that smart tutoring system systems can eliminate shortcomings of the traditional education systems by providing learning environments which are more flexible and complete even attaching emotion to enhanced student performance as well as overall wellness. The system's main features include scheduling and automated enrollment, virtual tutoring with real-time emotion recognition, and personalized tutor recommendations. To do this, researchers employed Convolutional Neural Networks (CNN) for emotion recognition, a content-based filtering algorithm, and prescriptive analytics for personalized tutor matching; the system recognizes students' emotional states and analyzes unique learning needs. The emotion recognition method analyzes pupils' facial movements in various emotional states to adapt or reinforce the mode of education. The content-based filtering algorithm, on the other hand, pairs students with tutors whose knowledge matches both the subject matter and the student's preferred learning technique. The system was evaluated using ISO 25010 criteria, which prioritized functional suitability, performance efficiency, usability, dependability, and security. Participants' responses (n=100) demonstrated primarily positive outcomes in these categories, with mean scores ranging from 3.82 to 4.33 on a 5-point Likert scale. Although the system achieved its primary objectives, the neutral findings indicate that there is still potential for improvement in some areas. This study proposes employing CNN and content-based filtering algorithms to enhance educational practices by creating a more adaptable, personalized, and emotionally responsive learning environment.