The Effects of Automated Writing Evaluation (AWE)+Human Feedback on the Quality of Argumentative Writing by Chinese EFL Learners

Nowadays, Chinese EFL learners are increasingly using automated writing evaluation (AWE) to provide feedback on their writing. However, AWE is relatively inadequate for providing elaborate feedback on the global aspects of writing that require human judgment. Thus, how to combine AWE with human feedback is a significant issue worth exploring. Regarding the effects of AWE+human feedback, cohesion and coherence are rarely studied. Thus, this study aimed to address that gap. This research employed a quasi-experimental study with a quantitative method to address AWE+human feedback. It also aimed to compare the effects of traditional feedback with AWE+human feedback modes, that is, teacher-only, AWE+teacher (AT), and AWE+peer+teacher (APT), on EFL learners’ writing quality in terms of holistic score, cohesion, and coherence. A total of 90 EFL learners from three intact classes of English major were randomly assigned to the control and experimental groups. The control group received only teacher feedback. The experimental groups received AT feedback and APT feedback in their writing process, respectively. Two instruments, iWrite and Coh-Metrix, were used to collect the data. Results showed that all feedback types improved holistic scores, coherence, and cohesion, with the APT model producing the most significant improvements across these dimensions. The APT group demonstrated particularly high holistic scores. It enhanced sentence-level coherence and lexical cohesion, suggesting that integrating AWE, peer, and teacher feedback provides a comprehensive and effective approach to developing writing proficiency.