Automated Examination System Using Natural Language Processing

This work suggests an automated testing system that creates and assesses questions using Natural Language Processing (NLP). The system analyzes textual content and generates pertinent exam questions using methods including Named Entity Recognition (NER) and Part-of-Speech (POS) tagging. Subjective responses are also graded using machine learning models such as Support Vector Machines (SVM) based on semantic similarity metrics. The primary objective of this framework is to improve assessment accuracy and minimize employee workload by streamlining the examination process. The model's effectiveness in academic environments is demonstrated through validation using real-world educational datasets.