Actionable companion · Assessment and evidence of learning

From evidence to district action: Digital feedback via free ChatGPT within the reciprocal teaching style: improving fundamental handball skills and students' attitudes among university beginners

AI-assisted editorial implementation guide. The district actions are proposed applications, not findings or recommendations attributed to the original authors. No additional peer review is asserted.

Evidence and context

Confirm the study population, setting and task before applying its findings to your district.

Original authors’ abstract, reproduced under the linked source license:

Abstract Introduction Digital technologies and artificial intelligence offer new opportunities to enhance teaching and learning processes in physical education. However, empirical evidence on the pedagogical use of ChatGPT-based feedback in skill-based sport instruction remains limited. This study examined the effectiveness of integrating ChatGPT-based digital feedback within the Reciprocal Teaching Style (RTS) to improve fundamental handball skills and students' attitudes in higher education. Methods A randomized pre-test–post-test control group design was used. Fifty-six undergraduate students enrolled in a third-level university handball course, with no prior formal handball training, were randomly allocated to either an experimental group receiving ChatGPT-based digital feedback embedded within Reciprocal Teaching Style or a control group using reciprocal teaching with peer feedback only. Both groups completed a structured 15-session instructional program over one academic semester. ChatGPT was used to generate structured corrective feedback based on predefined performance criteria, with mandatory manual analysis and human supervision to verify feedback accuracy. Data were collected using standardized physical fitness tests, expert-validated performance checklists assessing seven fundamental handball skills, and a students' attitudes scale. Analysis of covariance was conducted while controlling for pre-test scores. Results Statistically significant differences were found in favor of the experimental group across all assessed handball skills (p < .001), with medium to very large effect sizes (partial η2 = .33–.87). All results remained significant after Bonferroni adjustment, and post-hoc power analysis indicated high statistical power (≥.95). Students receiving ChatGPT-based feedback demonstrated higher mean scores across cognitive, affective, and behavioral attitude dimensions, including motivation, enjoyment, perceived usefulness, and intention to continue using AI-supported feedback. Conclusion Integrating ChatGPT-based digital feedback within reciprocal teaching enhances technical skill acquisition and supports favorable learning-related attitudes in university physical education. This approach provides a practical pedagogical model for improving feedback quality and instructional efficiency in skill-based sport courses, particularly in large-class settings, when supported by structured procedures and human oversight. Keywords: AI-supported feedback, artificial intelligence in education, ChatGPT, handball skills, higher education, physical education, reciprocal teaching style, teaching

A 90-day district pilot

1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
2. Days 16–30 · Design. Redesign one low-stakes assessment: require a first attempt, an AI-assisted revision, a source-check log and a short oral explanation. Use the same rubric for the comparison task. Name an accountable owner and set the baseline, success threshold and budget before implementation.
3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
4. Days 61–90 · Decide. Blind-score reasoning, factual accuracy and unaided transfer on a fresh task. Record suspected misconduct separately from demonstrated evidence. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Ahmed Hassan Rakha. Digital feedback via free ChatGPT within the reciprocal teaching style: improving fundamental handball skills and students' attitudes among university beginners. Frontiers in Sports and Active Living (2026-03-25). https://doi.org/10.3389/fspor.2026.1772502

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.