Conceptualize the Domain Knowledge Space in the Light of Cognitive Skills

Abstract

In this paper, we propose an approach that can improve the quality of pedagogies based on Bloom's Taxonomy (BT) cognitive theory. Theoretically, any domain knowledge can be learned and taught at multiple cognitive domain levels. Moreover, other cognitive domain levels might be called, for learn specific domain knowledge. If we know the dependencies between the domain knowledge, many interesting pedagogical applications are possible. However, until now, the relationship levels between domain knowledge are highly sophisticated and required tedious human judgment to be deduced. BT theory has been explored in the psychological sciences paradigm, but has not been examined automatically. No comprehensive computer science map is currently available. This paper, explores how the BT- relationships between various domain knowledge is automatically extracted. A Bloom Topic Graph (BTG) that encodes concept space is extracted. BTG provides concept space connected as BT cognitive relationships. Our approach utilizes verbs to discover the BT cognitive relationships between computer sciences, domain knowledge. We evaluate the BT cognitive relationships using ground truth, and our approach achieves an accuracy of average 65-75%, which is significantly high.