A Multilingual Sentiment Analysis Approach For Educational Institution Evaluation Based On Student Feedbacks

Abstract

This research offers a transformative approach to teacher evaluation in educational institutions by integrating deep learning techniques with multilingual sentiment analysis framework. Using advanced natural language processing algorithms, the computer analyses extensive datasets of student comments, including both English and Hinglish expressions, to identify a faculty member's various strengths and weaknesses. Deep learning models play a vital role in detecting complex patterns in this dataset, providing meaningful understanding of students' perception. The system not only displays a graphical representation of the evaluation results, showing the percentage of positive and negative feedback, but also provides a dynamic and contextual interpretation of the feedback. By capturing momentary emotions and feelings expressed by students, this holistic approach contributes to a comprehensive assessment of multilingual students' teacher performance and course satisfaction. Furthermore, the integration of deep learning technologies, facilitating real-time adaptation, ensuring a responsive and proactive evaluation process, represents a paradigm shift in teacher evaluation methods and taking the education sector towards a technologically advanced and student-centric future.