BMC PSYCHOLOGY, cilt.2026, sa.1, ss.1-29, 2026 (SSCI, Scopus)
The primary purpose of this study is to investigate the impact of using ChatGPT as a feedback mechanism on enhancing primary school students' poetry writing skills and attitudes towards poetry. In this study, a quasi-experimental design model with a pretest-posttest control group, a quantitative research method, was employed. In this study, conducted during the 2024-2025 academic year, 60 primary school fourth-grade students (30 experimental, 30 control) aged 10 years formed the study group for the research. During the six-week implementation period, students in the experimental group received ChatGPT-supported formative feedback on their poems and engaged in revision activities based on this feedback, while the control group participated in poetry writing activities without ChatGPT support. Data were analyzed using independent samples t-tests, paired samples t-tests, and analysis of covariance (ANCOVA). The results indicated a statistically significant difference in favor of the experimental group in posttest poetry writing skill scores when pretest scores were controlled (p< .001). In addition, students in the experimental group demonstrated significantly more positive attitudes toward poetry compared to the control group (p< .001). These findings suggest that ChatGPT-supported formative feedback may contribute to improvements in both poetry writing skills and attitudes toward poetry among primary school students.