A Comparative Study on Part-of-Speech Taggers’ Performance on Examination Questions Classification According to Bloom’s Taxonomy

Abstract Examination questions classification according to Bloom’s Taxonomy uses Natural Language Processing (NLP) approach, a series of text processing approach that generally can divided into the keywords identification stage and then identified levels stage. Since this NLP is pipeline processes, stage’s performance in term accuracy affecting subsequent - subsequently limits final classification. The mainly depending on effectiveness Part-Of-Speech (POS) tagging. Thus, paper aims identify best performing POS tagger enhance tagger’s with rule-based achieve high benefit keyword accuracy. Perceptron Stanford are selected be evaluated their identifying randomly 200 examination from STEM subjects. This has observed tagging 80.5%. Some rules applied improve further 91.5%.