A Neutrosophic Event-Indexed Framework for Evaluating Sports Classroom Teaching Effectiveness Based on Big Data and Artificial Intelligence

Assessing teaching effectiveness in sports classrooms is complicated by uncertain, incomplete, and often conflicting data collected from wearable sensors, computer vision, and AI-based platforms. Conventional statistical and fuzzy methods fail to represent such indeterminacy explicitly. To address this challenge, we propose an event-indexed neutrosophic framework that models each pedagogical action as a discrete event rather than a temporal sequence. Central to this framework is the Neutrosophic Pedagogical Effectiveness Index (NPEI), which fuses multimodal classroom evidence using plithogenic aggregation of neutrosophic triplets. To support this index, we introduce five event-indexed models: neutrosophic queueing for feedback allocation, neutrosophic Lévy flights and random walks for skill and engagement trajectories, neutrosophic renewal processes for practice–feedback cycles, and neutrosophic martingales for fairness analysis. Simulation results demonstrate that the proposed approach outperforms classical and fuzzy methods by capturing indeterminacy, ensuring robustness against incomplete data, and providing a rigorous mechanism for detecting bias in AI-supported evaluation. This study offers a novel and mathematically rigorous paradigm for sports education analytics, enabling fairer and more comprehensive assessments of teaching effectiveness.