A dynamic evaluation method for ethical awareness in metaverse-based educational environments using hybrid Bayesian sequential models.

Metaverse-based educational environments exhibit highly dynamic and interactive learning processes in which learners' ethical awareness evolves through latent developmental stages and abrupt behavioural shifts. Traditional static assessment approaches fail to capture such temporal dynamics. To address this limitation, this study proposes a hybrid Bayesian sequential modelling framework for dynamic evaluation of ethical awareness, using fully simulated longitudinal behavioural sequences designed to mimic realistic learning patterns in metaverse-based educational environments. The framework integrates Kalman filtering, Bayesian Online Change-Point Detection (BOCPD), and a duration-aware Hidden Semi-Markov Model (HSMM) to construct a reproducible time-series modelling pipeline. Kalman filtering is employed to estimate smoothed latent ethical trajectories, BOCPD identifies structural transitions triggered by behavioural fluctuations, and HSMM models developmental stages by incorporating explicit state-duration distributions, thereby reducing spurious short-term transitions. In addition, an interrupted time-series model with propensity score matching (ITS + PSM) is used to estimate the causal effects of instructional interventions.Experimental results demonstrate that the proposed hybrid Bayesian model sensitively detects key change points within metaverse learning contexts, yields stable stage-inference results, demonstrates the methodological capability of the proposed framework to support future intervention analysis. This work provides an interpretable, traceable, and reproducible methodological approach for evaluating ethical awareness in dynamic digital learning environments and offers valuable implications for ethical governance in metaverse-based education.