Abstract This study evaluates the efficacy of Chinese Automated Writing Correction Feedback (AWCF) platforms in enhancing writing performance among Chinese as a Second Language (CSL) learners against the backdrop of emerging generative AI tools like ChatGPT. Employing data from an intermediate CSL course at an Ivy League university, the paper scrutinizes selected Chinese AWCF platforms, such as Meta XiezuoCat, for their accuracy, effectiveness, and instructional potential. The analysis juxtaposes AWCF feedback withChatGPT responses and instructor assessments, revealing both the strengths and limitations of these platforms. The findings indicate that existing Chinese AWCF platforms exhibit noticeable limitations in CFL writing support but hold considerable potential for future development. Despite limitations in current corpus and accuracy compared with Generative AI such as ChatGPT, AWCF’s one-stop service model in error correction significantly reduces the cost of prompt engineering, while its feature of allowing “noticing” can help enhance students’ metalinguistic awareness. This finding also highlights the critical need for AWCF platforms to improve their utility by incorporating expansive and authentic CSL learner data.
Read full abstract