An automatic classifier for exam questions with WordNet and Cosine similarity

Abstract

The learning objectives, learning activities and assessment are very much interrelated. Assessment helps to evaluate students learning achievement. Poorly designed assessments usually fail to examine the achievement of intended learning outcome of a course. There are different taxonomies that have been developed to identify the level of the assessment being practiced such as Bloom's and SOLO. In this research we have studied the use of WordNet with Cosine similarity algorithm for classifying a given exam question according to Bloom's taxonomy learning levels. WordNet similarity algorithm depends on the extracted verbs from exam question. Cosine similarity algorithm was based on identification of question patterns of exam question. It consists of tag pattern generation module, grammar generation module, parser generation and cosine similarity checking module. This algorithm was helpful to classify the exam question where verbs were not present in exam questions. Exam questions taken from courses at the Department of Computing and Information Systems at Wayamba University were used as a basis for a performance comparison, with the autonomous system providing classifications that were consistent with those provided by domain experts on approximately 71% of occasions.