Using multimodal learning analytics as a formative assessment tool in AI-assisted physical education: a case study of Baduanjin teaching

Introduction Traditional formative assessment in physical education (PE) often lacks objectivity and fails to capture the intricate multimodal dynamics of instructional behaviors. This study validates a Multimodal Learning Analytics (MMLA) framework to decode teaching effectiveness in a peer-coaching context using the traditional Chinese exercise, Baduanjin. Methods We analyzed synchronous data from 20 instructional dyads ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"> <mml:mi>N</mml:mi> <mml:mo>=</mml:mo> <mml:mn>20</mml:mn> </mml:math> ), combining kinematic pose estimation (MediaPipe), speech fluency metrics (Whisper), and facial emotion recognition (OpenFace). Results Results from Spearman correlations and Mann-Whitney U tests revealed a “Precision-Economy” instructional archetype: high-performing instructors were characterized by superior kinematic fidelity ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"> <mml:msub> <mml:mi>r</mml:mi> <mml:mi>s</mml:mi> </mml:msub> <mml:mo>=</mml:mo> <mml:mn>.52</mml:mn> </mml:math> ) and verbal economy ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M3"> <mml:msub> <mml:mi>r</mml:mi> <mml:mi>s</mml:mi> </mml:msub> <mml:mo>=</mml:mo> <mml:mn>.47</mml:mn> </mml:math> ), rather than sheer feedback volume or emotional intensity. Counter-intuitively, excessive corrective feedback negatively correlated with learner skill gains ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M4"> <mml:msub> <mml:mi>r</mml:mi> <mml:mi>s</mml:mi> </mml:msub> <mml:mo>=</mml:mo> <mml:mo>−</mml:mo> <mml:mn>.41</mml:mn> </mml:math> ), suggesting a cognitive load interference effect. Discussion These findings challenge the “more-is-better” pedagogical assumption and demonstrate that AI-driven analytics can objectively quantify the tacit mechanisms of embodied instruction, offering a scalable tool for teacher training and developing countries seeking to modernize PE assessment, while acknowledging the necessity for further validation in open-skill sports contexts.

Authors

Institutions

Publication Details

Journal
Frontiers in Education
Published
2026-03-23
DOI
https://doi.org/10.3389/feduc.2026.1744594
Primary Topic
Physical Education and Pedagogy
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Using multimodal learning analytics as a formative assessment tool in AI-assisted physical education: a case study of Baduanjin teaching

Xiaoman Wen, TongKai Guan, BiXia Huan, Renee Shiun Yee Chew
Frontiers in Education
Physical Education and Pedagogy
article

Using multimodal learning analytics as a formative assessment tool in AI-assisted physical education: a case study of Baduanjin teaching

Xiaoman Wen, TongKai Guan, BiXia Huan, Renee Shiun Yee Chew
article en

Abstract

Introduction Traditional formative assessment in physical education (PE) often lacks objectivity and fails to capture the intricate multimodal dynamics of instructional behaviors. This study validates a Multimodal Learning Analytics (MMLA) framework to decode teaching effectiveness in a peer-coaching context using the traditional Chinese exercise, Baduanjin. Methods We analyzed synchronous data from 20 instructional dyads ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M1"> <mml:mi>N</mml:mi> <mml:mo>=</mml:mo> <mml:mn>20</mml:mn> </mml:math> ), combining kinematic pose estimation (MediaPipe), speech fluency metrics (Whisper), and facial emotion recognition (OpenFace). Results Results from Spearman correlations and Mann-Whitney U tests revealed a “Precision-Economy” instructional archetype: high-performing instructors were characterized by superior kinematic fidelity ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M2"> <mml:msub> <mml:mi>r</mml:mi> <mml:mi>s</mml:mi> </mml:msub> <mml:mo>=</mml:mo> <mml:mn>.52</mml:mn> </mml:math> ) and verbal economy ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M3"> <mml:msub> <mml:mi>r</mml:mi> <mml:mi>s</mml:mi> </mml:msub> <mml:mo>=</mml:mo> <mml:mn>.47</mml:mn> </mml:math> ), rather than sheer feedback volume or emotional intensity. Counter-intuitively, excessive corrective feedback negatively correlated with learner skill gains ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" id="M4"> <mml:msub> <mml:mi>r</mml:mi> <mml:mi>s</mml:mi> </mml:msub> <mml:mo>=</mml:mo> <mml:mo>−</mml:mo> <mml:mn>.41</mml:mn> </mml:math> ), suggesting a cognitive load interference effect. Discussion These findings challenge the “more-is-better” pedagogical assumption and demonstrate that AI-driven analytics can objectively quantify the tacit mechanisms of embodied instruction, offering a scalable tool for teacher training and developing countries seeking to modernize PE assessment, while acknowledging the necessity for further validation in open-skill sports contexts.

Frontiers in EducationVol. 11
INTI International University (MY), Jimei University (CN)
Quality Education
Openalex Percentile: Top 13%
Physical Education and Pedagogy
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.