Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models

As chatbots evolve from scripted responders to reasoning companions, their role in language education is rapidly shifting. Yet, while their presence is expanding, a deeper understanding of how they interact—not just respond—with learners remains elusive. This systematic review repositions interactio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunfei Du, Barry Lee Reynolds
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Acta Psychologica
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0001691825006201
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849248082871451648
author Yunfei Du
Barry Lee Reynolds
author_facet Yunfei Du
Barry Lee Reynolds
author_sort Yunfei Du
collection DOAJ
description As chatbots evolve from scripted responders to reasoning companions, their role in language education is rapidly shifting. Yet, while their presence is expanding, a deeper understanding of how they interact—not just respond—with learners remains elusive. This systematic review repositions interaction as the core of chatbot-assisted language learning, drawing on 100 peer-reviewed studies published between 2009 and 2024. Through a three-phase grounded coding approach to extract and synthesize these literature, we identify four distinct interaction styles, such as interlocutor, narrator, entertainer, and facilitator, each shaping engagement across pedagogical, affective, and cognitive domains. We find that large language models (LLMs) have broadened the educational affordances of chatbots, particularly in writing, speaking, and emotional support. However, their potential to foster higher-order thinking remains largely untapped. Limitations such as hallucination, bias, and ethical risks are seldom addressed in practice, underscoring the need for more critical integration. We argue that effective use depends not only on technological sophistication, but on prompt design, emotional connection, and teachers as ethical gatekeepers.
format Article
id doaj-art-ddc7903fa09843bfa61a4f01b52098fe
institution Kabale University
issn 0001-6918
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Acta Psychologica
spelling doaj-art-ddc7903fa09843bfa61a4f01b52098fe2025-08-20T03:58:00ZengElsevierActa Psychologica0001-69182025-09-0125910530710.1016/j.actpsy.2025.105307Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language modelsYunfei Du0Barry Lee Reynolds1School of Languages and Communication Studies, Chongqing University of Technology, Chongqing, China; Faculty of Education, University of Macau, Taipa, Macau SAR, China; Centre for Data Science, University of Macau, Taipa, Macau SAR, ChinaFaculty of Education, University of Macau, Taipa, Macau SAR, China; Centre for Data Science, University of Macau, Taipa, Macau SAR, China; Corresponding author at: Room 1014, E33, Faculty of Education, University of Macau, Taipa, Macau SAR, China.As chatbots evolve from scripted responders to reasoning companions, their role in language education is rapidly shifting. Yet, while their presence is expanding, a deeper understanding of how they interact—not just respond—with learners remains elusive. This systematic review repositions interaction as the core of chatbot-assisted language learning, drawing on 100 peer-reviewed studies published between 2009 and 2024. Through a three-phase grounded coding approach to extract and synthesize these literature, we identify four distinct interaction styles, such as interlocutor, narrator, entertainer, and facilitator, each shaping engagement across pedagogical, affective, and cognitive domains. We find that large language models (LLMs) have broadened the educational affordances of chatbots, particularly in writing, speaking, and emotional support. However, their potential to foster higher-order thinking remains largely untapped. Limitations such as hallucination, bias, and ethical risks are seldom addressed in practice, underscoring the need for more critical integration. We argue that effective use depends not only on technological sophistication, but on prompt design, emotional connection, and teachers as ethical gatekeepers.http://www.sciencedirect.com/science/article/pii/S0001691825006201Large language models (LLMs)Language learningChatbotInteractionChatGPT
spellingShingle Yunfei Du
Barry Lee Reynolds
Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
Acta Psychologica
Large language models (LLMs)
Language learning
Chatbot
Interaction
ChatGPT
title Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
title_full Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
title_fullStr Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
title_full_unstemmed Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
title_short Rooted in and beyond interaction: A systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
title_sort rooted in and beyond interaction a systematic review of interactive affordances of chatbots for language learning amidst the rise of large language models
topic Large language models (LLMs)
Language learning
Chatbot
Interaction
ChatGPT
url http://www.sciencedirect.com/science/article/pii/S0001691825006201
work_keys_str_mv AT yunfeidu rootedinandbeyondinteractionasystematicreviewofinteractiveaffordancesofchatbotsforlanguagelearningamidsttheriseoflargelanguagemodels
AT barryleereynolds rootedinandbeyondinteractionasystematicreviewofinteractiveaffordancesofchatbotsforlanguagelearningamidsttheriseoflargelanguagemodels