Generation of Bloom’s taxonomy-based complex-level questions using knowledge graph

In the landscape of educational technology, the present scenario in question generation often involves static and predefined assessments that may not adequately gauge students’ diverse cognitive abilities. The relevance of a knowledge graph in this context lies in its ability to capture the inherent connections and hierarchies within a domain, fostering a more intelligent and context-aware question generation process. This research proposes a novel approach to question generation, leveraging the knowledge graph. The knowledge graph serves as a dynamic representation of interconnected concepts, offering a structured framework for understanding relationships between topics. This, in turn, enables a more nuanced and contextually relevant selection of keywords for question formulation. Unlike traditional question generation methods, this model harnesses the power of semantic relationships encoded in the knowledge graph to align questions with Bloom’s Taxonomy levels, ensuring a spectrum of complexity. This innovative approach not only modernizes question generation but also aligns assessments more closely with real-world problem-solving scenarios, ultimately contributing to a more effective and personalized learning experience.