LANKAVALASA SHANMUKHA RAO, KALLEPALLI RAJYA LAXMI, BOTCHA TEJESWARARAO, HOBBILI KIRAN KUMAR, Mr.S.V.R MURTHY 03 03 The traditional method of evaluating academic answer sheets especially descriptive or subjective responses is a manual and laborintensive task that often suffers from inconsistencies evaluator fatigue human bias and significant delays in providing results to students As educational institutions worldwide handle increasing volumes of examinations across multiple subjects and academic levels the need for an intelligent efficient and scalable solution to automate the evaluation process has become critical This paper proposes an AIbased answer script evaluation system that leverages cuttingedge technologies in Natural Language Processing NLP machine learning and semantic analysis to assess written student responses against predefined model answers The system processes both student and model answers through comprehensive NLP preprocessing including tokenization stopword removal and lemmatization before computing TFIDF vector representations Semantic similarity between answers is computed using cosine similarity providing a contentbased score that goes beyond simple keyword matching to understand meaning and context Additionally the system incorporates spelling and grammar correction modules using language models and evaluates response coherence and logical structure through sentence flow analysis The final score is computed as a weighted combination of semantic similarity 60 grammar quality 20 and coherence 20 calibrated against expert human evaluators Evaluation on 500 answerkey pairs across 5 academic subjects demonstrates a Pearson correlation coefficient of 091 with expert evaluators reducing evaluation time by 92 from an average of 15 minutes per paper to 12 seconds while ensuring perfect scoring consistency with interrater reliability 10 Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026