USTW Vs. STW: A Comparative Analysis for Exam Question Classification based on Bloom’s Taxonomy

Bloom’s Taxonomy (BT) is widely used in educational institutions to produce high-quality exam papers evaluate students’ knowledge at different cognitive levels. However, manual question labeling takes a long time, and not all evaluators are familiar with BT. The researchers worked automate the classification process based on BT as solution. Enhancement term weighting one of ways increase accuracy while working text data. past work focused unsupervised (USTW) schemes. supervised (STW) schemes showed effectiveness but were addressed studies classification. As result, this study STW classifying questions using Hence, research performed comparative analysis between USTW for TF-ICF, TF-IDF-ICF, TF-IDF-ICSDF, whereas comparison TF-IDF, ETF-IDF, TFPOS-IDF. This Support Vector Machines (SVM), Na¨?ve Bayes (NB), Multilayer Perceptron (MLP) train model. Accuracy F1 score result. experiment result that overall, scheme TF-ICF outperformed other schemes, followed by ETF-IDF. Both ETF-IDF TFPOS-IDF standard TFIDF. outcome indicates future direction where combination may BT-based