Article: A quantitative evaluation model of English classroom interaction fairness driven by modal data distillation Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.36 pp.17 - 34 Abstract: Fairness in English classroom interaction is crucial for teaching quality and equity. Traditional assessment approaches are often limited. This study introduces a novel quantitative evaluation model using multimodal data distillation. It integrates heterogeneous data sources, constructs a joint representation space, and extracts key fairness indicators. Knowledge distillation transfers knowledge from a multimodal teacher model to a lightweight student model, achieving efficient compression and deployment. Validated on over 150 hours of real classroom data from 30 middle school English classes, the model achieves 92.3% accuracy in recognising teacher attention distribution. Its Gini coefficient error for student speaking opportunity is below 0.05, outperforming benchmarks. The compressed model retains only 40% of the original parameters, increases inference speed by 3.1 times, and maintains 94.7% core accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: A quantitative evaluation model of English classroom interaction fairness driven by modal data distillation

Authors: Guanguan Zeng; Man Li

Addresses: The School of Foreign Languages, Shanghai Zhongqiao Vocational and Technical University, Shanghai, 201514, China ' The School of Foreign Languages, Shanghai Zhongqiao Vocational and Technical University, Shanghai, 201514, China

Abstract: Fairness in English classroom interaction is crucial for teaching quality and equity. Traditional assessment approaches are often limited. This study introduces a novel quantitative evaluation model using multimodal data distillation. It integrates heterogeneous data sources, constructs a joint representation space, and extracts key fairness indicators. Knowledge distillation transfers knowledge from a multimodal teacher model to a lightweight student model, achieving efficient compression and deployment. Validated on over 150 hours of real classroom data from 30 middle school English classes, the model achieves 92.3% accuracy in recognising teacher attention distribution. Its Gini coefficient error for student speaking opportunity is below 0.05, outperforming benchmarks. The compressed model retains only 40% of the original parameters, increases inference speed by 3.1 times, and maintains 94.7% core accuracy.

Keywords: classroom interaction fairness; multimodal learning; knowledge distillation; quantitative evaluation models; educational equity.

DOI: 10.1504/IJICT.2026.153011

International Journal of Information and Communication Technology, 2026 Vol.27 No.36, pp.17 - 34

Received: 23 Oct 2025
Accepted: 08 Dec 2025
Published online: 17 Apr 2026 *

Title: A quantitative evaluation model of English classroom interaction fairness driven by modal data distillation

Keep up-to-date