Author Information
Jomar Ruiz, Polytechnic University of the Philippines, PhilippinesAbstract
This study developed and evaluated Math Tagumpay, a Bayesian-Fuzzy hybrid Intelligent Tutoring System (ITS) designed for Grade 3–4 mathematics in the Philippines. Addressing the urgent need for innovative instructional approaches in a context where 82% of Grade 4 students fall below minimum proficiency levels, the research employed a descriptive-quantitative methodology with 10 mathematics teachers from Bataan Province. The system implements a novel sequential architecture where Bayesian Knowledge Tracing (BKT) parameters serve as inputs to a Fuzzy Logic engine to manage the partial understanding states characteristic of young learners. The evaluation revealed exceptional technical performance, with System Accuracy achieving a weighted mean of 4.30 (94% positive response) and System Timeliness reaching 4.20 (94% positive response). The Technology Acceptance Model (TAM) assessment yielded an overall weighted mean of 4.04 (85% positive response), with Attitude Toward Using (4.26) and Perceived Usefulness (4.22) emerging as primary drivers of acceptance. While Perceived Ease of Use (3.68) was identified as an area for improvement, the findings validate that sophisticated AI can be successfully adapted for resource-constrained environments through cultural sensitivity and curriculum alignment. The study concludes that the hybrid AI approach effectively addresses the complexity of elementary mathematics learning and provides a scalable framework for enhancing instructional effectiveness in the Philippine educational system.
Paper Information
Conference: ACE2025Stream: Design
This paper is part of the ACE2025 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
To cite this article:
Ruiz J. (2026) Adoption of Bayesian Knowledge Tracing With Fuzzy Logic in the Development of Personalized Math Learning System for Grade 3 and 4 ISSN: 2186-5892 – The Asian Conference on Education 2025: Official Conference Proceedings (pp. 1719-1726) https://doi.org/10.22492/issn.2186-5892.2026.131
To link to this article: https://doi.org/10.22492/issn.2186-5892.2026.131
Comments
Powered by WP LinkPress