期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2015
卷号：76
期号：3
出版社：Journal of Theoretical and Applied
摘要：Bloom's Taxonomy is a classification of learning objectives within education that educators set for students. The cognitive domain within this taxonomy is designed to verify a student's cognitive level during a written examination. An experiment was designed to investigate student�s cognitive level, by developing rules to determine the categorization of questions based on Bloom's Taxonomy (BT). A sample of 135 questions collected from final examination past questions from FTSM, UKM. All questions has been analyzed by Computer Science subject matter experts to identify cognitive category based on BT. Rules are developed by analyzing the syntactic structure from the text questions. Next, some adjustment are made to utilize hybrid ability of rules and statistical approach. This rule-based approach applies Natural Language Processing (NLP) techniques to identify important keywords and verbs, which may assist in the identification of the category of a question. The advantage of this approach is that statistical classifier will assist the categorization when questions are not categorized by the rules. This approach gives better flexiblity when a set of 64 rules are developed for programming question domain. The result yeilds 86% for the average F1 for the hybrid technique. The outcome of this study suggest that the combined technique is capable of identifying the correct cognitive category of BT.
