Aug 27 – 29, 2026
University of Foreign Language Studies, The University of Danang, Vietnam
Asia/Ho_Chi_Minh timezone
Repositioning English: From Foreign to Second Language

Vocabulary in ChatGPT-Generated Reading Materials: Opportunities and Challenges for Emerging ESL Education in Vietnam

Not scheduled
30m
University of Foreign Language Studies, The University of Danang, Vietnam

University of Foreign Language Studies, The University of Danang, Vietnam

Oral Presentation Technology and L2 Learning Parallel Oral Presentations

Speaker

Ms Nhat Ha Nguyen (University of Science and Education - The University of Danang)

Description

English language education in Vietnam is expected to move from EFL to ESL, requiring learners to be frequently exposed to large amounts of level-appropriate English input beyond traditional classroom-based textbooks. ChatGPT can be an effective tool to facilitate this transition by producing a large number of extensive reading materials within a short time. However, few studies have examined its potential. This study investigated the lexical profile of ChatGPT-generated texts targeting learners at CEFR levels from A1 to C2. We created six corpora from texts generated by ChatGPT for each CEFR level and analysed their lexical profiles with RANGE (Heatley et al., 2002) and the BNC/COCA 25,000-word lists (Nation, 2012). The results showed that regardless of the target CEFR level, the lexical profile of ChatGPT-generated texts followed typical lexical profile, with high-frequency words constituting the largest percentage, followed by mid and low-frequency words. Moreover, ChatGPT-generated texts for lower levels (A1, A2, B1) were less lexically demanding than those for higher levels (B2, C1, C2). These findings indicate that ChatGPT could be a useful tool for creating extensive reading materials to support language development among students in Vietnam in the transition from EFL to ESL. However, we also found that ChatGPT-generated texts for the A1 and A2 levels required the same vocabulary sizes to those targeting the B1 level, whereas the figures for C1 were slightly smaller than expected. This finding highlights the importance of further checking and adjusting ChatGPT-generated texts to better tailor them to learners’ language proficiency.

Biography

Nhat Ha Nguyen Nhat Ha Nguyen is a recent graduate from the University of Leeds. She has presented at several national and international conferences in Vietnam and the UK such as BAAL Vocabulary SIG Annual Conference 2024. Her current research interests include corpus linguistics, vocabulary studies, and TESOL materials. Currently, she is a lecturer at University of Science and Education - The University of Da Nang.

Xuechun Huang is a PhD candidate at the School of Education, University of Leeds. Her research interests include vocabulary studies, technology-enhanced language learning, and translanguaging. She is a CELTA-qualified English language teacher and a teaching assistant for undergrad and graduate modules at the University of Leeds. She is the Event Coordinator at Open Applied Linguistics. She has won the Best Student Work-in-progress Presentation Award at the BAAL Vocabulary SIG Annual Conference 2024.

Thi Ngoc Yen Dang is an Associate Professor in Language Education at the University of Leeds, UK. Her research interests include vocabulary studies and corpus linguistics. Her articles have been published in various journals such as Applied Linguistics, Language Learning, Language Teaching, Studies in Second Language Acquisition, TESOL Quarterly, Language Teaching Research, and System.

Affiliate type University

Author

Ms Nhat Ha Nguyen (University of Science and Education - The University of Danang)

Co-authors

Prof. Thi Ngoc Yen Dang (University of Leeds) Ms Xuechun Huang (University of Leeds)

Presentation materials

There are no materials yet.