This quasi-experimental study investigates the effectiveness of AI-generated contextual texts as extracurricular resources for vocabulary acquisition among 16 Chinese tenth-grade students with documented lexical difficulties. Grounded in the New Curriculum Standards' emphasis on contextualized vocabulary learning and the comprehensible input hypothesis, the research compared a traditional word-list memorization approach (control group) with an AI-mediated contextual learning approach using ChatGPT 3.5-generated passages (treatment group). Over three treatment cycles, participants engaged in 20-minute after-class study sessions, followed by productive vocabulary post-tests and semi-structured interviews. Despite non-significant statistical differences in post-test scores (p > .05) attributable to limited sample size and treatment duration, convergent analysis of quantitative and qualitative data yielded pedagogically significant findings. AI-generated texts demonstrated capacity to: (1) scaffold lexical learning through thematically coherent, difficulty-calibrated contexts aligned with the "i+1" principle; (2) promote deeper semantic encoding via output-driven assessment tasks; and (3) function as schematic bridges integrating new vocabulary with existing knowledge frameworks. Qualitative feedback revealed that while the control group experienced rapid engagement decline and lexical attrition, the treatment group reported enhanced contextual inferencing, accelerated acquisition, and sustained motivational appeal, though concerns about long-term sustainability and learner autonomy emerged. Four evidence-based pedagogical implications are proposed: hybrid resource integration combining AI texts with explicit phonological instruction; standards-aligned technology mediation; systematic strategy-based instruction; and transformation of AI output into varied productive exercises. Study limitations include small sample size, absence of delayed post-tests, and restricted student-AI interaction. Future research should employ longitudinal designs, delayed retention measures, and learner-controlled AI models to establish robust effect sizes and scalability.

Liu Yumei, Jin Zixi. An Investigation of the Effectiveness of AI-Generated Contextual Texts for Extracurricular Vocabulary Acquisition among Tenth-Grade Students. Frontiers in Educational Research (2025), Vol. 8, Issue 10: 208-218. https://doi.org/10.25236/FER.2025.081031.

[1] Gui, T., Xi, Z., Zheng, R., Wang, J., Zhang, Y., & Wang, X. (2024). A survey on the robustness of deep learning-based natural language processing. Chinese Journal of Computers, 47(1), 90–112.

[2] Laufer, B., & Nation, I. P. (1999). A vocabulary size test of controlled productive ability. Language Testing, 16(1), 36–55.

[3] Leung, J., Pataranutaporn, P., Danry, V., & Zhu, J. (2024). Putting things into context: Generative AI-enabled context personalization for vocabulary learning improves learning motivation. In Proceedings of the CHI conference on human factors in computing systems (pp. 11–16). Association for Computing Machinery.

[4] Liang, E. (2018). A study on the effect of vocabulary memorization under the background of senior high school English morning reading (Unpublished master's thesis). Central China Normal University.

[5] Ministry of Education of China. (2022). Digital literacy for teachers (p. 3). China Education Publishing & Media Group.

[6] Ministry of Education of the People's Republic of China. (2020). Senior high school English curriculum standards (2017 edition, 2020 revision). People's Education Press.

[7] Nation, I. S. P. (1990). Teaching and learning vocabulary. Heinle & Heinle Publishers.

[8] Nation, P., & Beglar, D. (2007). A vocabulary size test. The Language Teacher, 31(7), 9–12.

[9] Shen, X. (2022). A comparative study of reading texts in PEP and FLTRP senior high school English textbooks (Unpublished master's thesis). Huaibei Normal University.

[10] Vu, D. V., & Peters, E. (2022). Learning vocabulary from reading-only, reading-while-listening, and reading with textual input enhancement: Insights from Vietnamese EFL learners. RELC Journal, 53(1), 85–100.

[11] Wang, M. (2011). A survey of English teachers' textbook use in senior high schools. Journal of Foreign Languages School of Shandong Normal University (Basic English Education), 13(5), 34–37.

[12] Wang, X. (2022). A study on the application of the palace memory strategy in senior high school English vocabulary teaching (Unpublished master's thesis). Southwest University.

[13] Wen, Y. (2022). Design of an AI-powered seamless vocabulary learning for young learners. In Proceedings of the 30th International Conference on Computers in Education (pp. 659–661). Asia-Pacific Society for Computers in Education.

[14] Wilkins, D. A. (1972). Linguistics in language teaching. MIT Press.

[15] Zhou, H. (2023). A study on the auxiliary application of ChatGPT in college English vocabulary teaching. Journal of Social Science of Jiamusi University, 41(6), 192–194.