Table 2_Digital feedback via free ChatGPT within the reciprocal teaching style: improving fundamental handball skills and students' attitudes among university beginners.docx

IntroductionDigital 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.
MethodsA 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.
ResultsStatistically 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.
ConclusionIntegrating 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.