Adult learners using the closed-loop ITS improved significantly across all seven BARS presentation dimensions over a 30-day practice window (Cohen's d = 0.39–0.90)¶

Claim · All claims
Evidence · 1 study · design r2 · q3 · i2 medium
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i2 In a 30-day pre–post field study with 204 adult learners, posttest BARS scores were higher than pretest scores on all seven dimensions, with the largest gains in delivery-related skills (Nonverbal Expressiveness d = 0.82; Overall Rating d = 0.90). → Hung-Yue Suen and Kuo-En Hung 2026

Evidence¶

Hung-Yue Suen and Kuo-En Hung 2026¶

Hung-Yue Suen and Kuo-En Hung. (2026). An Interpretable Closed-Loop Intelligent Tutoring System for Multimodal Affective Feedback in Asynchronous Presentation Training. IEEE Transactions on Learning Technologies. https://doi.org/10.1109/TLT.2026.3693864

q3 · i2 · design · r2

Pre–post field study of 204 adult learners recruited from partner MOOC platforms who practiced with the system for 30 days; paired-samples t-tests (Table IV) show Cohen's d from 0.39 (Content) to 0.90 (Overall Rating), with "the latter showing more noticeable shifts" for delivery-related elements.

"As shown in Table IV, oral presentation performance was higher at posttest than at pretest across all assessed dimensions. Changes were observed in both structure-related aspects of presentation and delivery-related elements, with the latter showing more noticeable shifts."

Discussion¶

Related Claims¶

• SHAP modality attributions aligned with each BARS dimension's behavioral focus, supporting interpretable feedback — related
• Learners showed reliable pre–post changes in facial, vocal, and lexical expressive signals after sustained system use — related
• Multimodal XGBoost models achieved rubric-aligned scoring comparable to expert ratings, and no single modality approached multimodal performance — related
• Practice frequency, not cumulative usage time, was strongly associated with posttest presentation performance after controlling for baseline and demographics — related