Volume 29 Number 2, February 2025 Special Issue: Indigenous Languages and Less Commonly Taught Languages (LCTLs) with Technology Using an AI-powered chatbot for improving L2 Korean grammar: A comparison between proficiency levels and task types

Using an AI-powered chatbot for improving L2 Korean grammar: A comparison between proficiency levels and task types

Repository record updated on:
Jan. 29, 2025, 2:02 a.m.
Database record updated on:
Feb. 12, 2025, 11:34 p.m.
Last Harvested on:
Feb. 12, 2025, 11:34 p.m.
bitstream:
[['https://scholarspace.manoa.hawaii.edu/bitstreams/da0c656b-3354-4571-b53d-fc836408cd93/download', '29_02_10125-73614.pdf']]
bitstream_txt:
[['https://scholarspace.manoa.hawaii.edu/bitstreams/6e9f8c96-7211-44ca-888b-bfc5eaf6b817/download', 'full_text']]
collection:
Volume 29 Number 2, February 2025 Special Issue: Indigenous Languages and Less Commonly Taught Languages (LCTLs) with Technology
contributor.author:
Shin, Ji-young Choi, Yujeong
date.accessioned:
2025-01-29T01:59:43Z
date.available:
2025-01-29T01:59:43Z
date.issued:
2025-02-01
description.abstract:
The use of AI-powered chatbots has recently been extensively examined for second language (L2) learning. While their positive effects have been widely reported regarding L2 English learning, studies involving less commonly taught languages (LCTLs) are scant. The current study incorporated an AI chatbot called Iruda in L2 Korean teaching, to improve Korean lexico-grammar, while examining moderation of proficiency levels and task types. Sixty-six students engaged with AI chatbot-incorporated tasks with half of the grammar points of the course curriculum throughout the semester. During their final exam, students’ grammar was assessed through selected-response (SR) and constructed-response (CR) tasks (sentence completion and sentence composition). Using a paired-sample t-test, we compared item mean differences between grammatical features practiced with chatbot-incorporated and conventional methods. Items related to chatbot practice showed a significantly higher mean (t(65) = 4.29, p <.0001). Follow-up regression and repeated-measures ANOVAs revealed greater changes by chatbot practice among students with lower pre-existing Korean proficiency and significant moderation of task types with higher SR item means. Students’ perceptions were also positive. The study demonstrated the effectiveness of chatbot-enhanced instruction for LCTLs, while suggesting nuanced application for learners of varied proficiency levels and different task types.
endingpage:
160
format.extent:
29
identifier.citation:
Shin, J., & Choi, Y. (2025). Using an AI-powered chatbot for improving L2 Korean grammar: A comparison between proficiency levels and task types. Language Learning & Technology, 29(2), 132–160. https://hdl.handle.net/10125/73614
identifier.issn:
1094-3501
identifier.uri:
https://hdl.handle.net/10125/73614
number:
2
publicationname:
Language Learning & Technology
publisher:
University of Hawaii National Foreign Language Resource Center Center for Language & Technology
rights:
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
rights.uri:
https://creativecommons.org/licenses/by-nc-nd/4.0/
site_url:
/item/10125-73614/
startingpage:
131
subject:
AI chatbots Less Commonly Taught Languages Teaching Grammar Korean as a Foreign Language
title:
Using an AI-powered chatbot for improving L2 Korean grammar: A comparison between proficiency levels and task types
type:
Article
type.dcmi:
Text
volume:
29