Artificial intelligence in language learning: biometric feedback and adaptive reading for improved comprehension and reduced anxiety

• Biometric data analysis, including heart rate variability (HRV) and eye-tracking metrics, provided objective evidence supporting the platform’s efficacy in reducing stress levels and promoting more efficient reading behaviors: "By the end of the intervention, the experimental group's HRV surpassed that of the control group, demonstrating successful adaptation and decreased stress." (Results, Biometric data analysis—HRV analysis) vs "HRV | Group (Experimental) | -0.85 (0.10) | -8.50 | <0.001" (Results, Table 5, HRV rows). At equal covariates, the group difference changes from -0.85 to -0.85 - 0.20 = -1.05, while experimental and control changes are +0.10 and +0.30 respectively. → Not supported by the paper's own data
• Quantitative results revealed significant improvements in reading comprehension, motivation, anxiety reduction, and cognitive load management among participants using the AI platform compared to the control group: "At baseline, both groups were comparable across all variables, indicating successful random assignment" (Results, Descriptive statistics and preliminary analyses) vs "Reading comprehension | Group (Experimental) | 13.80 (1.20) | 11.50 | <0.001" (Table 5, Reading comprehension Group (Experimental)). Comparing Table 1's unadjusted reading difference of 65.4 - 64.8 = 0.6 with the conditional coefficient 13.80 suggests a mismatch, but interpreting it as a baseline discrepancy assumes unresolved model coding and adjustment. → Effect on result unclear
• Effect sizes indicated large to moderate impacts of the intervention across all measured variables: "Wilks' Lambda = 0.32, F(4, 295) = 34.65, p < 0.001, η² = 0.68" (Results, Multivariate analysis of variance (MANOVA)). For the stated two-group MANOVA, F = ((1 - 0.32)/0.32) × (295/4) = 156.71875 rather than 34.65. → Conclusion holds
• Biometric data analysis, including heart rate variability (HRV) and eye-tracking metrics, provided objective evidence supporting the platform’s efficacy in reducing stress levels and promoting more efficient reading behaviors: "(fixation duration: t(298) = 13.45, p < 0.001; regressions: t(298) = 14.78, p < 0.001)" (Results, Eye-tracking data, fixation and regression paragraph). Using 150 participants per arm, fixation |t| = 65/sqrt((30² + 35²)/150) approximately 17.27 and regression |t| = 2.6/sqrt((1.1² + 1.5²)/150) approximately 17.12. → Conclusion holds
• Biometric data analysis, including heart rate variability (HRV) and eye-tracking metrics, provided objective evidence supporting the platform’s efficacy in reducing stress levels and promoting more efficient reading behaviors: "The average fixation duration was 250 ms (SD = 32 ms) for the experimental group" (Methods, Validation of biometric tools (Eye-tracking technology)) vs "shorter fixation durations (M = 225 ms, SD = 30 ms)" (Results, Biometric data analysis (eye-tracking, Table 4)). The validation subsection reports experimental fixation duration of 250 ms whereas Results reports 225 ms, without establishing whether these summarize the same measurement occasion. → Effect on result unclear

Ethics approval, consent, competing interests, and data access upon request are declared, but prospective registration, a primary-outcome hierarchy, and participant-flow accounting are not reported. Weekly questionnaires are described without corresponding longitudinal reporting, and legal-guardian consent wording is unexplained for the adult sample.

Conflict of interest: declared · Ethics approval: declared · Data availability: declared

92 references in manuscript 78 of 78 checkable references found in an index 14 have no canonical index record — counted, but not index-checkable 1 mistyped DOI matched to the cited work by its details 13 references confirmed by manual review

References not verified automatically are resolved manually within 24 hours.

No retraction or expression of concern found in Crossref (includes Retraction Watch).