Generative AI Empowering College English Writing: An Empirical Study on Syntactic Complexity and Lexical Richness

Junyi Wang

doi:10.47297/taposatWSP2633-456902.20260708

PDF
Export
Share
Collection
Album

Generative AI Empowering College English Writing: An Empirical Study on Syntactic Complexity and Lexical Richness

Volume 7, Issue 8

Views: 0 Downloads: 0

Generative AI Empowering College English Writing: An Empirical Study on Syntactic Complexity and Lexical Richness
Generative AI Empowering College English Writing: An Empirical Study on Syntactic Complexity and Lexical Richness
School of Foreign Languages, Guangzhou College of Commerce, Guangzhou, Guangdong, 511363, China
Vol. 7, Issue 8, Pages: 11-15(2026)
Published：30 August 2026
DOI：10.47297/taposatWSP2633-456902.20260708
Accepted：

Scan QR Code

Wang Junyi.Generative AI Empowering College English Writing: An Empirical Study on Syntactic Complexity and Lexical Richness[J].Theory and Practice of Science and Technology,2026,07(08):11-15.
DOI：

Wang Junyi.Generative AI Empowering College English Writing: An Empirical Study on Syntactic Complexity and Lexical Richness[J].Theory and Practice of Science and Technology,2026,07(08):11-15. DOI： 10.47297/taposatWSP2633-456902.20260708.

摘要

Abstract

Drawing on the Output Hypothesis and the Noticing Hypothesis

this study employs a single-group pretest-posttest quasi-experimental design with 108 first-year non-English major students at a college to quantitatively analyze the effects of "AI + teacher" dual-line feedback on syntactic complexity and lexical richness in English writing

using the NeoSCA tool. Six indicators—MLS

MLC

C/S

LS1

and MSTTR—were selected. Results showed that MLS (Z = 6.415

p < 0.001)

MLC (t = -11.726

p < 0.001)

and LD (t = -3.827

p < 0.001) improved significantly; C/S (t = 6.247

p < 0.001) decreased significantly; while MSTTR (p = 0.102) and LS1 (p = 0.445) showed no significant differences. These findings indicate that dual-line feedback is effective in promoting phrase expansion and content-word density enhancement

but does not facilitate clause embedding or advanced lexical expansion

exhibiting a selective improvement pattern characterized by "increased length without structural complexification." This study provides purely quantitative empirical evidence for AI-assisted English writing instruction.

关键词

Keywords

references

Guo, Q., Feng, R. L., & Hua, Y. F. (2023). Applications and potential risks of ChatGPT in English academic paper writing and teaching. Technology Enhanced Foreign Language Education , 2 , 18–23.

Lu, X. F., & Xu, Q. (2016). The L2 syntactic complexity analyzer and its applications in second language writing research. Foreign Language Teaching and Research , 48 (3), 409–420.

Lu, X. (2010). Automatic analysis of syntactic complexity in second language writing. International Journal of Corpus Linguistics , 15 (4), 474–496.

Norris, J. M., & Ortega, L. (2009). Towards an organic approach to investigating CAF in instructed SLA: The case of complexity. Applied Linguistics , 30 (4), 555–578.

Ortega, L. (2003). Syntactic complexity measures and their relationship to L2 proficiency: A research synthesis of college-level L2 writing. Applied Linguistics , 24 (4), 492–518.

Schmidt, R. (199 0). The role of consciousness in second language learning. Applied Linguistics , 11 (2), 129–158.

Swain, M. (1985). Communicative competence: Some roles of comprehensible input and comprehensible output. In S. Gass & C. Madden (Eds.), Input in second language acquisition (pp. 235–253). Newbury House.

Warschauer, M., & Grimes, D. (2008). Automated writing assessment in the classroom. Pedagogies: An International Journal , 3 (1), 22–36.

Wei, S., & Li, L. Y. (2023). Research on AI-assisted L2 writing feedback: A case study of ChatGPT. Foreign Languages in China , 20 (3), 33–40.

Zhou, L. (2015). The effects of online English writing platforms on undergraduates' syntactic writing competence. Technology Enhanced Foreign Language Education , 5 , 26–29.