Artificial Intelligence for Pedagogical Decision-making: A Comparative Study of Probabilistic and Rule-based Learner Models
AI, Computer Science and Robotics Technology · 04.08.2026 · 5
DOI: 10.5772/acrt.20250240 ↗Kurz gefasst
Fachartikel in der Zeitschrift AI, Computer Science and Robotics Technology, online erschienen am 04.08.2026. Verfasst von Mouenis Anouar Tadlaoui und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Learner modeling is a foundational component of adaptive educational systems and intelligent tutoring environments. Over the past three decades, research in artificial intelligence for education has produced a spectrum of modeling approaches designed to support pedagogical decision-making, ranging from early rule-based systems to advanced probabilistic inference models. Despite significant progress, a comprehensive comparative analysis of these two paradigms within modern AI-enhanced adaptive learning environments remains limited. This article addresses this gap by conducting an in-depth comparative examination of rule-based learner models and probabilistic models, with a specific focus on Bayesian networks and multi-entity Bayesian networks. Drawing on a systematic review of the literature and on empirical examples from adaptive hypermedia, programming education, and learner analytics, the study evaluates both paradigms along six dimensions: representational capacity, inference mechanisms, uncertainty management, scalability, interpretability, and personalization accuracy. Results indicate that while rule-based models retain value in structured and deterministic domains, probabilistic approaches offer superior flexibility, predictive power, and robustness in handling incomplete or noisy learner data. The paper concludes by proposing a hybrid probabilistic-rule framework and presenting implications for next-generation pedagogical decision-support systems.
Zitieren
APA
Tadlaoui, M. A., Chekour, M., & Mahdi, K. (2026). Artificial Intelligence for Pedagogical Decision-making: A Comparative Study of Probabilistic and Rule-based Learner Models. AI, Computer Science and Robotics Technology, 5. https://doi.org/10.5772/acrt.20250240
Vancouver
Tadlaoui MA, Chekour M, Mahdi K. Artificial Intelligence for Pedagogical Decision-making: A Comparative Study of Probabilistic and Rule-based Learner Models. AI, Computer Science and Robotics Technology. 2026;5. doi:10.5772/acrt.20250240
BibTeX
@article{Tadlaoui2026,
author = {Tadlaoui, Mouenis Anouar and Chekour, Mohammed and Mahdi, Khalid},
title = {Artificial Intelligence for Pedagogical Decision-making: A Comparative Study of Probabilistic and Rule-based Learner Models},
journal = {AI, Computer Science and Robotics Technology},
year = {2026},
volume = {5},
doi = {10.5772/acrt.20250240}
}
EUVIMED