School of Foreign Studies, Northwestern Polytechnical University, China
Email: qiaohuixin@mail.nwpu.edu.cn (H.X.Q.); sophiayucheng@nwpu.edu.cn (F.L.)
*Corresponding author)
Manuscript received May 9, 2025; accepted September 5, 2025; published November 24, 2025.
Abstract—With the rapid advancement of technology, Artificial Intelligence (AI) has become an integral tool in education, particularly in language learning. This study examines the role DeepSeek as a feedback mechanism plays for improving junior high school English writing. Through a corpus-based analysis of 30 essays written by junior high school students, the study evaluates DeepSeek’s effectiveness in providing feedback across three key dimensions, namely, vocabulary, grammar, and discourse. The findings indicate that at the lexical level, DeepSeek provides contextualized corrections that help address Chinglish-related issues, leading to greater lexical accuracy and diversity. At the grammatical level, it identifies common errors and improves sentence structures, which facilitates a structured learning cycle of “error recognition → cognitive adjustment → knowledge internalization.” This process enhances linguistic coherence and overall writing accuracy. At the discourse level, DeepSeek aids in organizing ideas logically and fosters critical thinking, ultimately contributing to promote students’ language proficiency and cognitive development. As artificial intelligence continues to evolve, integrating AI-powered feedback into writing instruction presents new opportunities for facilitating language learning and improving writing proficiency for junior high school students.
Keywords—DeepSeek-assisted, junior-high school, English writing feedback
Cite: Huixin Qiao and Fei Liu, "Corpus-based Analysis on DeepSeek-Assisted Feedback in Junior High School English Writing,"
International Journal of Languages, Literature and Linguistics, vol. 11, no. 6, pp. 259-265, 2025.
Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).