T4. LEARNING ANALYTICS AND KNOWLEDGE FOR ADAPTIVE INTELLIGENCE
SCOPE:
Research at the intersection of learning analytics, knowledge modeling, and adaptive intelligence. Focus on how knowledge about learning processes is modeled, interpreted, and transformed into adaptive, explainable, and equitable decisions that enhance learning outcomes in dynamic ecosystems.
A. MODELING, REPRESENTATION & UNDERTANDING
Learner modeling; knowledge tracing; multimodal data fusion; graph-based representation learning; cognitive modeling; metacognitive state estimation; causal reasoning in learning; interpretable machine learning; knowledge graph construction; concept drift detection; feature engineering for education; semantic embedding of learning artifacts; self-regulated learning analytics; behavioral sequence mining; applications of data mining; latent skill discovery; explainable representation learning; cross-domain learner transfer; fine-grained temporal analytics; open learner models; ontology-driven learning data integration.
FOCUS: how learner knowledge, behavior, and cognition are represented and understood through interpretable, causal, and multimodal modeling approaches.
B. ADAPTIVE DECISIONONG & ACTIONABLE INTELLIGENCE
Deep learning and machine learning for tutoring systems; algorithms for data mining; supervised machine learning; reinforcement learning for pedagogy; causal intervention modeling; policy optimization for education; adaptive recommendation engines; curriculum sequencing; genetic algorithms; personalization algorithms; predictive early- warning systems; fairness-aware decision systems; dynamic feedback optimization; Bayesian knowledge updating; data-driven pedagogy design; continuous learning analytics pipelines; active learning for educational adaptation; explainable decision-support systems; educational simulation for policy design; assessment using computer vision; adaptive agent collaboration; user-controllable AI feedback; human-in-the-loop adaptation; scalable personalization frameworks; analytics-to-action evaluation metrics.
FOCUS: transforming analytic insights into adaptive, data-driven, and explainable interventions that optimize individual and ecosystem-level learning.