Paper Key : IRJ************132
Author: Kanishka Mahadev Shelke,Rutuja Mohan Rupanavar,Shraddha Rajendra Lokhande,Vaishnavi Umesh Humane,Prof. A. A. Bandgar
Date Published: 09 Apr 2025
Abstract
Educational assessment effectiveness depends on student-generated data that produces value by enhancing classroom quality. Feedback procedures based on manual assessments yield weak performance while taking up an excessive amount of time and showing subjective tendencies because various educators agree about the lengthy and subjective process. The AI-driven student feedback system utilizes Natural Language Processing (NLP) to carry out automated qualitative evaluations of feedback exactly as the research study proposes. Transformed student feedback undergoes sentimental analysis that supports topic modeling and keyword extraction to generate guidance for professors creating support plans. The feedback analysis system functions using Python to integrate NLTK and SpaCy and Transformers together with machine learning models and Python components to evaluate feedback emotions and extract main topics with required adjustments. The automated platform provides better perception of collected insights and conducts automated tasks to deliver unbiased feedback outcomes. The system supports educational institutions to create better decisions regarding instructional approaches that deliver improved student satisfaction results. Using NLP-based AI techniques creates an opportunity for academic feedback systems to build efficient objective systems to improve insight quality. Student feedback evaluations for teaching quality assessment stand as vital assessment methods which enhance academic results within educational institutions that provide higher education. Student feedback collection through traditional methods shows both substantial inefficiencies and human judgment elements before requiring substantial human labor. The research proposal introduces a technology infrastructure that uses NLP to automate student assessment of professor performance for improved evaluation processes. Python programming software together with NLTK and SpaCy and Transformational models from advanced NLP frameworks enable the system to evaluate feedback contents by locating both positive and negative performance elements which generate practical solutions.
DOI Requested