Computational Modeling of Educational Excellence: A Systems Approach to Integrating Artificial Intelligence with NAAC Revised Accreditation Framework

Abstract

The National Assessment and Accreditation Council (NAAC) accreditation process requires comprehensive evaluation of Self-Study Reports (SSRs) through Quantitative Metrics (QnM) and Qualitative Metrics (QlM). However, manual assessment of these metrics is time-consuming, labor-intensive, and prone to inconsistencies. This paper presents an integrated Artificial Intelligence (AI) based framework for automated SSR analysis, QnM score computation, QlM score prediction and report generation. The proposed system first computes QnM scores by extracting SSR responses and evaluating them against predefined NAAC benchmarks and metric weightages. Subsequently, the generated QnM scores are utilized to predict QlM scores using multiclass deep learning models, including Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Region-Based Convolutional Neural Networks (R-CNN). Experimental results demonstrate that the R-CNN model achieves superior performance with an accuracy of 98%. To further enhance institutional assessment, the framework integrates Natural Language Processing (NLP) to produces structured analytical reports through automated report generation modules and provides interactive user interfaces for real-time evaluation. The proposed framework significantly improves accuracy, consistency, scalability, and processing efficiency, offering a reliable decision-support solution for accreditation assessment and quality assurance in Higher Education Institutions.