METACOGNITIVE PLANNING STRATEGIES IN AI-DRIVEN SPEAKING PRACTICE: ENHANCING EFL LEARNERS’ FLUENCY AND SPEECH PREP
Keywords:
Keywords: Metacognitive planning, EFL oral fluency, Voice AI interaction, speech rate, silent pause reduction, cognitive load theory, Task-Based language teaching, learner autonomy, speech preparation strategies, Artificial Intelligence in PedagogyAbstract
This study investigates the impact of pre-task metacognitive planning strategies on English as a Foreign Language (EFL) learners’ oral fluency during interactive encounters with conversational Voice Artificial Intelligence (AI). While voice-based AI applications offer accessible, low-anxiety speaking practice, learners frequently experience cognitive overload, resulting in prolonged hesitations and fragmented speech when interacting without strategic preparation. Utilizing a quasi-experimental pre-test/post-test control group design, intermediate-level university students were divided into an experimental group, which employed a structured Metacognitive Planning Sheet prior to AI voice sessions, and a control group, which engaged in unguided AI conversations over a multi-week intervention period. Temporal fluency parameters – specifically speech rate and silent pause frequency – were measured alongside qualitative assessments of perceived cognitive load and speaking confidence. The findings revealed that learners utilizing pre-task metacognitive planning achieved a statistically significant increase in speech rate and a substantial reduction in unfilled silent pauses, markedly outperforming the control group. Qualitative data indicated that pre-task goal-setting and conversational anticipation reduced real-time cognitive processing strain, allowing learners to reallocate mental resources toward speech execution and discourse continuity. The paper concludes with pedagogical implications for integrating metacognitively scaffolded frameworks into AI-enhanced language learning environments.
References
1.Baddeley, A. (2000). The episodic buffer: A new component of working memory? Trends in Cognitive Sciences, 4(11), 417–423. https://doi.org/10.1016/S1364-6613(00)01538-2
2.Derakhshan, A., & Shirvan, M. E. (2023). Harnessing artificial intelligence in foreign language learning: Opportunities and cognitive challenges. Computers & Education, 198, 104765. https://doi.org/10.1016/j.compedu.2023.104765
3.Ellis, R. (2009). The differential effects of pre-task planning and on-line planning on L2 speaking performance. Applied Linguistics, 30(4), 474–509. https://doi.org/10.1093/applin/amp012
4.Flavell, J. H. (1979). Metacognition and cognitive monitoring: A new area of cognitive–developmental inquiry. American Psychologist, 34(10), 906–911. https://doi.org/10.1037/0003-066X.34.10.906
5.Foster, P., & Skehan, P. (1996). The influence of planning and task type on second language performance. Studies in Second Language Acquisition, 18(3), 299–323. https://doi.org/10.1017/S0272263100015048
6.Goh, C. C., & Burns, A. (2012). Teaching speaking: A holistic approach. Cambridge University Press.
7.Jeon, J. (2022). Exploring the pedagogical potential of AI voice assistants in developing EFL learners' oral fluency. Language Learning & Technology, 26(2), 45–63.
8.Levelt, W. J. (1989). Speaking: From intention to articulation. MIT Press.
9.Li, J., & Kim, L. (2024). Overcoming speech hesitation through conversational AI: Cognitive load and fluency outcomes in higher education. System, 121, 103210. https://doi.org/10.1016/j.system.2024.103210
10.Oxbrow, G. (2020). Metacognitive awareness and strategy instruction in oral production. International Journal of Applied Linguistics, 30(1), 112–129. https://doi.org/10.1111/ijal.12264
11.Skehan, P. (1998). A cognitive approach to language learning. Oxford University Press.
12.Sweller, J. (1988). Cognitive load during problem solving: Effects on learning. Cognitive Science, 12(2), 257–285. https://doi.org/10.1207/s15516709cog1202_4
13.Vandergrift, L., & Goh, C. C. (2012). Teaching and learning second language listening: Metacognitive awareness and strategy development. Routledge.
14.Wang, Y., & Choi, S. (2023). Generative AI and language education: A systematic review of voice-based interactive tools for oral communication. Educational Technology Research and Development, 71(4), 1823–1845. https://doi.org/10.1007/s11423-023-10255-w
15.Zimmerman, B. J. (2002). Becoming a self-regulated learner: An overview. Theory Into Practice, 41(2), 64–70. https://doi.org/10.1207/s15430421tip4102_2