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

Abstract

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

Content Analysis of the EFL Textbook Units According to Bloom’s Taxonomy: Between Theory and Practice

“…Taxonomy is another word for classification. According to Gani et al (2023) & Pratiwi (2015, taxonomy implies a hierarchy of classifications based on basic principles or rules. Bloom's taxonomy is a classification system for cognitive thinking skills.…”

“…Content analysis is a simple research approach that is used to analyze books, documents, etc. Content analysis is a type of qualitative study, which is defined as "a research method for the subjective interpretation of the content of text data through the systematic classification process of coding and identifying themes and patterns" (Gani et al, 2023;Hsieh & Shannon, 2005). Further, it is systematic reading for making replicable and valid inferences from texts or other symbolic matters.…”

Bloom’s Taxonomy based automatic Marathi question generation

“…Karamustafaoglu et al have classified biology questions as per Bloom's taxonomy by Biology teachers [47]. Various approaches, including naïve bayes, laplace smoothing [48], artificial neural networks [49], CNN [50], pre-trained language model [51], and rule-base [52] have been employed for question classification. The various types of context-based and grammarbased questions generated through the AQG model are depicted in Figures 5 and 6.…”

The Effects of Revised Bloom’s Taxonomy Enriched Instruction on EFL Learners’ Writing Performance in an Academic Writing Course

“…Since that time, RBT has been used officially to construct the curriculums considering the cognitive levels of learners. RBT has certain classifications which are remembering, understanding, applying, analysing, evaluating and creating (Gani, 2023). It can be clearly observed that it emphasizes the value of laying solid background before driving the learners to produce.…”