<![CDATA[Writing is one of the most challenging language skills for learners of English as a Foreign Language, particularly at the secondary school level, where limited instructional time and large class sizes often hinder the provision of effective individualized feedback. This condition creates a need for alternative feedback strategies that are both efficient and pedagogically sound. This study aimed to analyze and compare the effectiveness of automated written corrective feedback based on artificial intelligence. The study employed a quantitative approach using a quasi-experimental non-equivalent control group pretest–posttest design. The participants consisted of 82 eighth-grade students divided into two intact classes, with 40 students assigned to the control group and 42 students to the experimental group. Data were collected through recount text writing tests administered as pretests and posttests, using an analytic scoring rubric covering content, organization, vocabulary, grammar, and mechanics. Data analysis was conducted using descriptive statistics and an independent samples t-test at a significance level of 0.05. The results indicated no statistically significant difference in recount text writing ability between students who received Automated Written Corrective Feedback and those who received teacher-provided Written Corrective Feedback. These findings suggest that both types of feedback are relatively equivalent in supporting the development of students’ writing skills. Overall, the study concludes that both AWCF and WCF can be flexibly implemented in writing instruction, with the implication that AI-based feedback technologies represent a viable alternative in contexts characterized by limited instructional resources.]]>
Copyrights © 2025
