Student modeling — computational representations of learner knowledge and affect — is advanced by knowledge-tracing, llm-student-modeling-memory, engagement-intensity-learner-modeling, and history-aware-student-simulation: LLMs add semantic depth to classical models (educational-measurement, intelligent-tutoring).
Related Pages
- cross-subject-validity-delayed-start — Cross-subject predictive validity of delayed start behavior as a generalizable learner behavior signal
- surfacing-isolated-learners — links here
- physiological-signals-exam-outcomes-ml -- Random forest predicts exam outcomes from physiological signals as well as deep learning with better interpretability
- self-efficacy-tutoring-learning — Self-Efficacy and Favorability Shape Learning from Tutoring
- correct-answer-trap-misconceptions -- Fine-tuned classifiers detect only 57% of hidden student misconceptions, while reasoning models reach 84% but at 8:1 false alarms — a detect-verify-escalate pipeline with diagnostic follow-up questions is proposed.
- at-risk-students-ml-prediction -- Logistic regression and linear SVM achieve highest accuracy for predicting student attrition using academic, demographic, and enrollment data.
- skill-acquisition-without-temporal-info -- A neural framework predicts next-skill acquisition from snapshot CDM data using pseudo-temporal ordering via inclusion relations among skill sets.
- llm-item-difficulty-prediction — Cognitive episode modeling from LLM reasoning traces
- cogtax-cognitive-taxonomy — student modeling approaches
📎 9 other pages tagged student-modeling
- Analysis and Prediction of At-Risk Students Using Machine Learning Algorithms
- Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
- Cross-Subject Predictive Validity for Learning Outcomes of Delayed Start Behavior
- Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs
- Estimating Learners' Skill Acquisition Without Temporal Information
- Interpretable Knowledge Tracing
- PersonaVLM: Long-Term Personalization for AI Tutors
- Reexamining the Cold-Start Problem in Knowledge Tracing Models and Implications for SafeInsights
- The Correct Answer Trap: Pedagogically-Grounded Detection and Feedback for Hidden Misconceptions