AI-GFCA students show better pronunciation, fluency and IELTS speaking predictor scores than AI-C students, but intonation does not differ¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1–r2 · q2 · i2 medium
Currency · newest study 2025 · checked against its sources 2026-10-29 (automated, 2 of 2 entries) · not reviewed by a person
Design limits · Darmawansah 2025: groups were assigned but students were analysed as independent · Darmawansah 2025 (2): groups were assigned but students were analysed as independent (read from the study by two models, 2026-10-29)

Subclaims¶

q2 i2 The AI-GFCA group had better pronunciation scores than the AI-C group. → Darmawansah 2025 q2 i? Intonation scores did not differ significantly between the AI-GFCA and AI-C groups. → Darmawansah 2025 (2)

Evidence¶

Darmawansah 2025¶

Darmawansah, D., Hwang, G.-J., Lin, C.-J., & Febiyani, F. (2025). An artificial intelligence-supported GFCA learning model to enhance L2 students' role-play performance, English speaking and interaction mindset. Education Tech Research Dev (2025) 73:1451–1479. https://doi.org/10.1007/s11423-025-10453-6

q2 · i2 · causal · r2

Mann–Whitney test on post-test pronunciation scores from the AI speaking app log profile (15 read sentences) in the 45-student quasi-experiment; pronunciation favored AI-GFCA with "r = 0.28".

"students in the AI-GFCA group (Mdn = 63) had better pronunciation scores than students in the AI-C group (Mdn = 55) with U = 168.00, z = − 1.934, p = 0.05, and r = 0.28."

Darmawansah 2025 (2)¶

Darmawansah, D., Hwang, G.-J., Lin, C.-J., & Febiyani, F. (2025). An artificial intelligence-supported GFCA learning model to enhance L2 students' role-play performance, English speaking and interaction mindset. Education Tech Research Dev (2025) 73:1451–1479. https://doi.org/10.1007/s11423-025-10453-6

q2 · i? · causal · r1

Null Mann–Whitney result for the intonation variable of the AI speaking assessment; no statistically significant group difference was detected and equivalence was not tested.

"In contrast, the intonation scores of the AI-GFCA group (Mdn = 65) and the AI-C group (Mdn = 49.5) did not show a significant difference (U = 175.50, z = − 1.761)."

Discussion¶

Related Claims¶

• Students using the AI-GFCA learning model outperform AI-supported conventional-learning peers in role-play performance at both measured tasks — related
• AI-GFCA students produce fewer L2 errors than AI-C students, with the advantage varying by error type and task — related
• CAPT software shows promising results for segmental pronunciation, while prosodic features and fluency still require further research and development — a broader claim this one bears on
• The learner's first language influences target-language pronunciation and is a significant factor in foreign accents, causing errors in aspiration, intonation, and rhythm — related