Your browser does not fully support modern features. Please upgrade for a smoother experience.
Artificial Intelligence in EFL Speaking Instruction: A Systematic Review of Pedagogical Design, Affective Conditions and Instructional Input: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor: Sareen Kaur Bhar

Speaking proficiency remains one of the most challenging skills for learners of English as a Foreign Language (EFL), particularly in contexts where sustained spoken interaction is limited. This systematic review synthesises 36 empirical studies (2015–2025) identified through a PRISMA-guided Scopus search to examine how artificial intelligence (AI)-mediated instruction supports EFL speaking development. The included studies were analysed according to AI modality, pedagogical integration, instructional input characteristics, and linguistic and affective outcomes. Findings indicate that AI tools—such as chatbots, automatic speech recognition systems, and large language models—consistently support affective outcomes, including reduced speaking anxiety and increased willingness to communicate. Improvements in fluency, pronunciation, and accuracy were frequently reported, particularly when AI tools were embedded within task-based and pedagogically structured instructional designs. However, evidence for sustained development of higher-order communicative competence was more variable. The review proposes a mediated input framework conceptualising AI as a design-sensitive instructional resource rather than an autonomous teaching agent.

  • artificial intelligence
  • EFL speaking
  • AI-assisted language learning
  • instructional input
  • speaking anxiety
  • pedagogical design
  • systematic review
Speaking proficiency is widely recognised as one of the most demanding skills for learners of English as a Foreign Language (EFL). Unlike receptive skills such as reading and listening, speaking requires learners to process linguistic input in real time while simultaneously managing accuracy, fluency, pronunciation, and affective factors such as confidence and anxiety [1][2]. In many EFL contexts, particularly those characterised by limited exposure to sustained or authentic interaction, learners continue to struggle to develop spoken competence despite years of formal instruction [3]. These persistent challenges have prompted renewed interest in instructional approaches that foreground learners’ access to meaningful language exposure as a foundation for oral language development.
Input-oriented approaches have long emphasised the role of comprehensible input in facilitating language acquisition, proposing that learners benefit when exposure to language precedes pressured or premature output [4][5]. From this perspective, sustained listening, reading, and interactional exposure enable learners to internalise linguistic patterns and establish form–meaning connections that support spoken production. Empirical research suggests that such approaches can contribute to gains in both fluency and accuracy in speaking [6]. However, in many instructional settings—particularly large, examination-driven classrooms—providing sufficiently rich, individualised, and frequent input remains a longstanding pedagogical constraint.
Recent advances in artificial intelligence (AI) have expanded the ways in which speaking opportunities and language exposure can be provided in EFL classrooms. Technologies such as conversational chatbots, automatic speech recognition systems, and large language models allow learners to engage in responsive, repeatable, and low-anxiety interaction beyond the temporal and spatial limits of classroom instruction [7][8]. A growing body of empirical research has examined the use of AI-mediated tools for speaking practice, pronunciation training, and automated feedback, often reporting improvements in oral fluency, accuracy, and learner confidence [9][10][11]. Despite this expanding evidence base, existing studies vary considerably in how AI is pedagogically implemented and theoretically interpreted.
As a result, the pedagogical role of AI in EFL speaking development remains insufficiently synthesised. In particular, there is limited clarity regarding how different forms of AI-mediated speaking support relate to established constructs in second language acquisition, including learners’ engagement with language input, interaction, and affective conditions for learning. Prior studies are frequently fragmented across technologies, learner populations, and outcome measures, with many emphasising short-term performance gains or learner perceptions rather than offering integrated, theory-informed interpretations [12]. This fragmentation has constrained the field’s ability to draw coherent conclusions about how AI-mediated speaking instruction functions across instructional contexts.
This systematic review addresses this gap by synthesising empirical studies on AI-mediated instruction for EFL speaking development. The review identifies recurring instructional functions, pedagogical approaches, and learning outcomes associated with AI-supported speaking activities. Drawing on input-oriented and task-based perspectives as interpretive lenses, the review further examines how AI-mediated practices may support learners’ engagement with spoken language and oral development under different instructional conditions. Rather than advancing prescriptive claims about AI’s instructional role, the review provides an evidence-informed synthesis intended to support theoretically grounded research and principled pedagogical decision-making.
This review is informed by three complementary theoretical perspectives from second language acquisition research: input-based theory, interactionist perspectives on language learning, and sociocultural approaches to mediated learning. Input-oriented frameworks emphasise the importance of comprehensible and meaningful exposure to language as a foundation for acquisition, while interactionist accounts highlight how participation in dialogue and feedback processes supports linguistic development. Sociocultural perspectives further stress the role of mediation, scaffolding, and instructional design in shaping learning outcomes. Together, these perspectives provide a coherent interpretive framework for analysing how AI-mediated speaking environments influence learner engagement with instructional input, interaction, and affective conditions for language development.
Accordingly, the review addresses the following research questions:
  • RQ1: What AI technologies and pedagogical approaches have been employed to support EFL/ESL speaking development, and how are these pedagogically positioned (practice, feedback, or interaction)?
  • RQ2: What linguistic and affective outcomes are associated with AI-supported speaking instruction, and under what instructional conditions are these outcomes sustained?
  • RQ3: What affordances and limitations of AI-mediated speaking instruction emerge when interpreted through input-oriented and task-based perspectives?
From an educational perspective, understanding how AI-mediated speaking activities are designed and embedded within instructional contexts is essential for translating technological potential into sustainable classroom practice.

This entry is adapted from the peer-reviewed paper 10.3390/encyclopedia6040074

References

  1. Bygate, M. Speaking. In The Cambridge Guide to Teaching English to Speakers of Other Languages; Carter, R., Nunan, D., Eds.; Cambridge University Press: Cambridge, UK, 2001; pp. 14–20.
  2. Thornbury, S. How to Teach Speaking; Longman: London, UK, 2005.
  3. Horwitz, E.K. Language anxiety and achievement. Annu. Rev. Appl. Linguist. 2001, 21, 112–126.
  4. Krashen, S.D. Principles and Practice in Second Language Acquisition; Pergamon: Oxford, UK, 1982.
  5. VanPatten, B. Input processing in second language acquisition. In Theories in Second Language Acquisition, 2nd ed.; VanPatten, B., Williams, J., Eds.; Routledge: London, UK, 2015; pp. 113–134.
  6. Ellis, R. The Study of Second Language Acquisition, 2nd ed.; Oxford University Press: Oxford, UK, 2008.
  7. Godwin-Jones, R. Using mobile technology to develop language skills and cultural understanding. Lang. Learn. Technol. 2018, 22, 1–17.
  8. MacIntyre, P.D.; Clément, R.; Dörnyei, Z.; Noels, K.A. Conceptualizing willingness to communicate in a L2: A situational model of L2 confidence and affiliation. Mod. Lang. J. 1998, 82, 545–562.
  9. Swain, M. Communicative competence: Some roles of comprehensible input and comprehensible output in its development. In Input in Second Language Acquisition; Gass, S.M., Madden, C.G., Eds.; Newbury House: Rowley, MA, USA, 1985; pp. 235–253.
  10. Long, M.H. The role of the linguistic environment in second language acquisition. In Handbook of Second Language Acquisition; Academic Press: San Diego, CA, USA, 1996.
  11. Gass, S.M.; Mackey, A. Input, Interaction, and Output in Second Language Acquisition; Lawrence Erlbaum: Mahwah, NJ, USA, 2007.
  12. McCarthy, M.J.; O’Keeffe, A. Research in the teaching of speaking. Annu. Rev. Appl. Linguist. 2004, 24, 26–43.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
Academic Video Service
Feedback