AI-Driven Rubrics for Academic Grading & Feedback Using Fuzzy Clustering & Attention Networks

Educational assessment has changed from “one size fits all” model to learner-centered, responsive, and adaptable dynamic rubrics and feedback procedures. Improved instructor-student communication and transparency boost, engagement and assessment confidence with dynamic rubrics. Dynamic rubrics could improve feedback and assessment. Pre-processed standard dataset texts are used. Pre-processed texts are delivered to Word2Vec to extract key features and vectorize them. Fuzzy clustering model with dynamically weighted rubrics evaluates the assignment. The dynamic rubric clearly outlines the assignment's evaluation criteria, and weights assist decide how much each criterion contributes to the overall grade using Foraging Phase Updated Addax Optimization. Subsequently, the assessment score is obtained, and based on this score, feedback generation is performed on the developed model using Generative Attention Long Short Term Memory. Finally, the developed model provides the optimal responses to the students by using the dynamic rubric with a deep learning model and an enhanced optimization algorithm. The experiment scores on two datasets observed over existing models shows average accuracy of 99.36% with 2.7% improvement over K-Means Clustering. Average MAE of 31.85%, reduced by 81% over K-Means. Average Efficiency increase by 21.30% over other models. Thus, the developed model is more effective and robust than the existing approaches.