Enhancing Educational Assessment Efficiency: An AIbased Approach to Automated Examination Evaluation

Abstract

Manually grading subjective papers is a difficult and time-consuming task. Lack of comprehension and acceptance
of the results is one of the biggest obstacles to employing artificial intelligence (AI) to analyse subjective articles.
There have been several attempts to grade responses from pupils using computer science. However, most of the
work uses specific words or traditional counts to achieve this. Furthermore, verified data sets are not enough.
Using a range of natural language processing, machine learning, and toolkits, including Wordnet, Word2vec, word
mover's distance (WMD), cosine comparison, multinomial naive bayes (MNB), and others, this study presents a
novel approach for automatically analysing descriptive responses and TF-IDF, or term frequency-inverse
document frequency. Answers are evaluated using keywords and solution statements, and grades are predicted
using a machine learning algorithm. Overall, the findings show that WMD and cosine are more comparable. The
machine learning system may be used independently once it has undergone the required training. Trial and error
results