This paper explores Knowledge Tracing (KT) and its role in modeling students’ knowledge progression over time. While traditional approaches such as Bayesian Knowledge Tracing and Deep Knowledge Tracing have established a solid foundation in this field, previous research often overlooked the complex interactions between problem features and learner behaviors. To address this gap, this paper introduces the Knowledge Tracking Model for Integrating Question Information and Learning Behaviour (IQILB-KT), a novel framework that enhances the precision of knowledge tracing in online educational systems. By integrating the effects of question characteristics and student behaviour via a channel attention mechanism, the model captures deeper insights into both question information and the learning process. Furthermore, the IQILB-KT model employs a Bottleneck Attention Module (BAM) to calculate learning behaviour synergies, replacing the previous reliance on covariance statistics. This enhances the stability and accuracy of the model when dealing with learning behaviour synergy data. Finally, the efficacy of the IQILB-KT model was validated through rigorous testing on two real-world datasets from the ASSISTments educational platform. The results demonstrate that the model outperforms all existing methods in predicting students’ future performance and tracking their knowledge states in real time.

This paper proposes a novel framework, HyperGAT-BERT-RAS, that integrates (1) a HyperGraph Attention Network (HyperGAT) with BERT for enhanced semantic representation; (2) a Reference Answer Set (RAS) constructed via clustering of full-score answers; and (3) Siamese Neural Networks (SNNs) for similarity-based scoring. Experiments on the Ohsumed and ASAP-5 datasets demonstrate that (i) HyperGAT-BERT achieves 72.95% accuracy on Ohsumed text classification, outperforming baseline HyperGAT by 3.28%, and (ii) the full HyperGAT-BERT-RAS achieves 78.66% accuracy and 0.7806 F1-score, with RAS contributing the most to performance gains. These improvements suggest the potential for more reliable scoring of diverse student answers, reduced teacher grading burden, and enhanced feasibility of AI-assisted formative assessment in real classrooms, although empirical validation with teachers and students is needed.

This paper proposes a novel framework, HyperGAT-BERT-RAS, that integrates: (1) a Hy perGraph Attention Network (HyperGAT) with BERT for enhanced semantic representa-tion; (2) a Reference Answer Set (RAS) constructed via clustering of full-score answers; (3) Siamese Neural Networks (SNNs) for similarity-based scoring; and (4) GPT-4-based data augmentation to address class imbalance. Experiments on the Ohsumed and ASAP-5 da-tasets demonstrate that: (i) HyperGAT-BERT achieves 0.7317 accuracy on Ohsumed text classification, outperforming baseline HyperGAT by 2.69%; (ii) the full Hyper-GAT-BERT-RAS achieves 0.7991 accuracy and 0.7956 F1-score, with RAS contributing the most to performance gains (4.34% accuracy drop when removed); (iii) GPT-4 augmentation improves Quadratic Weighted Kappa from 0.584 to 0.880 and minority-class (scores 2–3) F1 by 15.3%. These improvements translate into more reliable scoring of diverse student answers, reduced teacher grading burden, and enhanced feasibility of AI-assisted forma-tive assessment in real classrooms. Ablation and error analyses confirm the contribution of each component. The framework advances ASAG by synergizing graph-based relational modeling, pretrained language understanding, and knowledge-guided scoring.