Emotion Computation in English Classrooms Empowered by Digital Twins Through Multimodal Biosignal Integration and Dynamic Prediction of Learning Motivation
Year: 2025
Type: article
Abstract: The integration of digital twin technology with multimodal biosignal analysis presents transformative potential for next-generation classroom environments. Traditional methods for emotion and motivation modeling in educational settings often rely on unimodal data sources and static predictive frameworks, which struggle to capture the complex, dynamic interplay of cognitive, emotional, and linguistic factors in real time. These limitations hinder the ability of intelligent classroom systems to provide responsive, personalized learning experiences. To address these challenges, we propose a novel framework that models English language classroom interactions as structured optimization processes. This framework embeds learner states, engagement trajectories, and linguistic development into a unified mathematical formulation, enabling adaptive and interpretable learning interventions. Central to our approach are two core innovations: the Semantic Cognition Modulator (SCM) and the Adaptive Empowerment Policy (AEP). SCM is a latent space-based neural architecture designed to track and predict the evolution of learner competencies by fusing linguistic, emotional, and meta-cognitive inputs. AEP operates as a real-time optimization mechanism that adjusts instructional strategies dynamically, based on learners’ behavioral feedback and engagement patterns. We evaluate our framework within digitally twinned classroom simulations equipped with multimodal sensing technologies, including facial affect recognition, speech analysis, and attention tracking. Experimental results show that our method substantially improves prediction accuracy for learning motivation and supports higher levels of sustained student engagement compared to baseline models. These findings underscore the framework’s efficacy in enhancing the adaptability and precision of intelligent education systems, paving the way for more responsive and learner-centered classroom experiences.
Author: Haiyan Chen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W4412550908