Classroom Mood and Attention Monitoring System Enhancing Student Well Being

In the domain of education, the integration of machine learning methodologies for student assessment and stress detection has emerged as a critical area of investigation. This paper explores the application of computationally intelligent techniques, particularly sentiment analysis and natural language processing, for the analysis and interpretation of teachers’ textual feedback in academic reports. Through sentiment analysis, qualitative feedback is quantified, enabling a comprehensive evaluation of students’ academic progress encompassing behavioural aspects, attendance, and achievement. Moreover, this study investigates the correlation between learning behaviour data and classroom performance, emphasising the importance of analysing unstructured data including video, audio, and image inputs to comprehend students’ behaviours and learning patterns. Utilising big data technology and predictive modelling, this research aims to augment teaching efficacy, enhance learning outcomes, and establish a framework for real-time assessment of teachers’ performance. Furthermore, the project endeavours to develop a system capable of discerning students’ emotions and stress levels using machine learning algorithms. By analysing facial expressions and other behavioural indicators, the system endeavours to furnish timely feedback to both teachers and students, fostering a supportive learning milieu conducive to academic achievement. In essence, this research underscores the significance of harnessing advanced technologies such as machine learning, sentiment analysis, and predictive modelling to enrich student assessment, stress detection, and overall educational achievements.