Evaluating Adaptive Personalization of Educational Readings with Simulated Learners

arXiv cs.CL / 4/21/2026

📰 NewsDeveloper Stack & InfrastructureIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper proposes a theory-grounded framework to evaluate adaptive personalization of educational readings using simulated learners rather than live students.
It constructs a learning-objective/knowledge-component ontology from open textbooks, organizes it via a browser-based “Ontology Atlas,” and generates aligned reading–assessment pairs by labeling textbook chunks with ontology entities.
The simulated learners use a Construction–Integration-inspired memory model with factor-based reading variables, misconception revision, and a readability signal to produce answers from an explicit memory state.
Adaptation is driven by Bayesian Knowledge Tracing (BKT), and experiments across three subject ontologies show adaptive reading improves computer science results, produces mixed/uncertain effects in inorganic chemistry, and is neutral to slightly negative for general biology.
Overall, the study provides an evaluation system for adaptive reading personalization and highlights that benefits can be domain-dependent rather than universally positive.

Abstract

We present a framework for evaluating adaptive personalization of educational reading materials with theory-grounded simulated learners. The system builds a learning-objective and knowledge-component ontology from open textbooks, curates it in a browser-based Ontology Atlas, labels textbook chunks with ontology entities, and generates aligned reading-assessment pairs. Simulated readers learn from passages through a Construction-Integration-inspired memory model with DIME-style reader factors, KREC-style misconception revision, and an open New Dale-Chall readability signal. Answers are produced by score-based option selection over the learner's explicit memory state, while BKT drives adaptation. Across three sampled subject ontologies and matched cohorts of 50 simulated learners per condition, adaptive reading significantly improved outcomes in computer science, yielded smaller positive but inconclusive gains in inorganic chemistry, and was neutral to slightly negative in general biology.