Mining Cognitive Skills Levels of Knowledge Units in Text Using Graph Tringluarity Mining

Semantic analysis among knowledge units in the text is a very interesting problem in numerous applications. Beside the semantic relationships expressed in the text, relationships are also encoded in knowledge structures in our brains. However, the relationships among knowledge units are highly sophisticated and require a human judgment. In this paper, we propose a Graph-Tringluarity-based system for knowledge units' classification in the textual graph, which identifies the adapted Bloom's Taxonomy levels. Given knowledge units, the system discovers significant relationship types among them based on the cognitive skills. We evaluate and validate the system on three datasets (textbooks) by utilizing the knowledge units of a computer science domain. As a result, the proposed system succeeds to discover the hidden associations among knowledge units and classify them. Furthermore, the performance shows expressive centrality measures of knowledge units' analysis.