Classification of Questions and Learning Outcome Statements (LOS) Into Blooms Taxonomy (BT) By Similarity Measurements Towards Extracting Of Learning Outcome from Learning Material

摘要

Blooms Taxonomy (BT) have been used to classify the objectives of learningoutcome by dividing the learning into three different domains; the cognitivedomain, the effective domain and the psychomotor domain. In this paper, we areintroducing a new approach to classify the questions and learning outcomestatements (LOS) into Blooms taxonomy (BT) and to verify BT verb lists, whichare being cited and used by academicians to write questions and (LOS). Anexperiment was designed to investigate the semantic relationship between theaction verbs used in both questions and LOS to obtain more accurateclassification of the levels of BT. A sample of 775 different action verbscollected from different universities allows us to measure an accurate andclear-cut cognitive level for the action verb. It is worth mentioning thatnatural language processing techniques were used to develop our rules as toinduce the questions into chunks in order to extract the action verbs. Ourproposed solution was able to classify the action verb into a precise level ofthe cognitive domain. We, on our side, have tested and evaluated our proposedsolution using confusion matrix. The results of evaluation tests yielded 97%for the macro average of precision and 90% for F1. Thus, the outcome of theresearch suggests that it is crucial to analyse and verify the action verbscited and used by academicians to write LOS and classify their questions basedon blooms taxonomy in order to obtain a definite and more accurateclassification.