Pecha, a language practice peer: Guiding language learning interactions through large language models

The interaction hypothesis of second language acquisition (Long, 1981) states that negotiated interaction is necessary for language development. In many language learning contexts, educators and stakeholders seek to provide opportunities for learners to engage in meaningful real-life interactions t...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryan Lege, Euan Bonner, Takako Aikawa
Format: Article
Language:English
Published: Castledown Publishers 2024-12-01
Series:Technology in Language Teaching & Learning
Subjects:
Online Access:https://www.castledown.com/journals/tltl/article/view/1716
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122219689738240
author Ryan Lege
Euan Bonner
Takako Aikawa
author_facet Ryan Lege
Euan Bonner
Takako Aikawa
author_sort Ryan Lege
collection DOAJ
description The interaction hypothesis of second language acquisition (Long, 1981) states that negotiated interaction is necessary for language development. In many language learning contexts, educators and stakeholders seek to provide opportunities for learners to engage in meaningful real-life interactions that help them build linguistic, semantic, and rhetorical competence. However, the opportunities provided for interaction can vary in their degree of effectiveness and may only sometimes lead to increased language ability. If these interactions are scaffolded correctly, they can be tuned to maximize their benefits (Loewen & Sato, 2018). Unfortunately, this is not always practical from a temporal and economic perspective. Artificial intelligence (AI) could be the solution for providing learners with individualized, comprehensive assistance during their learning interactions. Accordingly, the authors developed a bespoke application that employs advanced natural language processing and large language model AI technologies to support learner interactions. The application was developed to support students in two different contexts: Kanda University of International Studies in Japan, where students study English, and Massachusetts Institute of Technology in the United States, where learners study Japanese. The rationale for creating the application and selecting its major features is discussed. This is followed by a discussion of how the application functions and how it will be used.  The authors will then discuss their plans for implementation into both informal and formal learning contexts at the two universities. They conclude by discussing potential limitations and plans for improving the application.
format Article
id doaj-art-f97e77fe33a2458ca6b4e89ea901c5e6
institution Kabale University
issn 2652-1687
language English
publishDate 2024-12-01
publisher Castledown Publishers
record_format Article
series Technology in Language Teaching & Learning
spelling doaj-art-f97e77fe33a2458ca6b4e89ea901c5e62024-12-15T02:52:56ZengCastledown PublishersTechnology in Language Teaching & Learning2652-16872024-12-016310.29140/tltl.v6n3.1716Pecha, a language practice peer: Guiding language learning interactions through large language modelsRyan Lege0Euan Bonner1Takako Aikawa2Kanda University of International StudiesKanda University of International StudiesMassachusetts Institute of Technology The interaction hypothesis of second language acquisition (Long, 1981) states that negotiated interaction is necessary for language development. In many language learning contexts, educators and stakeholders seek to provide opportunities for learners to engage in meaningful real-life interactions that help them build linguistic, semantic, and rhetorical competence. However, the opportunities provided for interaction can vary in their degree of effectiveness and may only sometimes lead to increased language ability. If these interactions are scaffolded correctly, they can be tuned to maximize their benefits (Loewen & Sato, 2018). Unfortunately, this is not always practical from a temporal and economic perspective. Artificial intelligence (AI) could be the solution for providing learners with individualized, comprehensive assistance during their learning interactions. Accordingly, the authors developed a bespoke application that employs advanced natural language processing and large language model AI technologies to support learner interactions. The application was developed to support students in two different contexts: Kanda University of International Studies in Japan, where students study English, and Massachusetts Institute of Technology in the United States, where learners study Japanese. The rationale for creating the application and selecting its major features is discussed. This is followed by a discussion of how the application functions and how it will be used.  The authors will then discuss their plans for implementation into both informal and formal learning contexts at the two universities. They conclude by discussing potential limitations and plans for improving the application. https://www.castledown.com/journals/tltl/article/view/1716Computer-Assisted Language Learning (CALL)artificial intelligenceAIinteractionlarge language modelsLLMs
spellingShingle Ryan Lege
Euan Bonner
Takako Aikawa
Pecha, a language practice peer: Guiding language learning interactions through large language models
Technology in Language Teaching & Learning
Computer-Assisted Language Learning (CALL)
artificial intelligence
AI
interaction
large language models
LLMs
title Pecha, a language practice peer: Guiding language learning interactions through large language models
title_full Pecha, a language practice peer: Guiding language learning interactions through large language models
title_fullStr Pecha, a language practice peer: Guiding language learning interactions through large language models
title_full_unstemmed Pecha, a language practice peer: Guiding language learning interactions through large language models
title_short Pecha, a language practice peer: Guiding language learning interactions through large language models
title_sort pecha a language practice peer guiding language learning interactions through large language models
topic Computer-Assisted Language Learning (CALL)
artificial intelligence
AI
interaction
large language models
LLMs
url https://www.castledown.com/journals/tltl/article/view/1716
work_keys_str_mv AT ryanlege pechaalanguagepracticepeerguidinglanguagelearninginteractionsthroughlargelanguagemodels
AT euanbonner pechaalanguagepracticepeerguidinglanguagelearninginteractionsthroughlargelanguagemodels
AT takakoaikawa pechaalanguagepracticepeerguidinglanguagelearninginteractionsthroughlargelanguagemodels