WordNet and Cosine Similarity based Classifier of Exam Questions using Bloom's Taxonomy

Assessment usually plays an indispensable role in the education and it is the prime indicator of student learning achievement. Exam questions are the main form of assessment used in learning. Setting appropriate exam questions to achieve the desired outcome of the course is a challenging work for the examiner. Therefore this research is mainly focused to categorize the exam questions automatically into its learning levels using Bloom's taxonomy. Natural Language Processing (NLP) techniques such as tokenization, stop word removal, lemmatization and tagging were used prior to generating the rule set to be used for this classification. WordNet similarity algorithms with NLTK and cosine similarity algorithm were developed to generate a unique set of rules to identify the question category and the weight for each exam question according to Bloom's taxonomy. These derived rules make it easy to analyze the exam questions. Evaluators can redesign their exam papers based on the outcome of this classification process. A sample of examination questions of the Department of Computing and Information Systems, Wayamba University, Sri Lanka was used for the evaluation; weight assignment was done based on the total value generated from both WordNet algorithm and the cosine algorithm. Identified question categories were confirmed by a domain expert. The generated rule set indicated over 70% accuracy.