SCAFFOLDING EFL SPEAKING PRACTICE: UNIVERSITY STUDENTS' ENGAGEMENT WITH GEMINI AI FEEDBACK
DOI:
https://doi.org/10.51878/language.v6i3.15004Keywords:
Umpan balik Gemini AI, praktik berbicara EFL, perancah digital, kelancaran berbicara, akurasi tata bahasaAbstract
The rapid development of generative artificial intelligence in language education offers new opportunities to provide immediate and personalized oral feedback; however, its use as digital scaffolding in interactive communication practice remains underexplored. This study aimed to explore how undergraduate English as a Foreign Language (EFL) students engage with generative AI-mediated feedback as a digital scaffolding mechanism during interactive oral communication practice. This qualitative case study involved three intermediate EFL university students at Institut Pendidikan Indonesia Garut, West Java. Data were collected through multi-session oral interactions and semi-structured retrospective interviews and analyzed using Braun and Clarke's six-phase thematic analysis. Vygotsky's Sociocultural Theory and Schmidt's Noticing Hypothesis served as theoretical foundations for understanding scaffolding processes, linguistic awareness, and students' oral interaction development. The findings revealed that Gemini AI functioned as both an affective and cognitive scaffold during speaking practice. Affectively, interaction with AI created a low-anxiety practice environment with minimal social pressure, thereby enhancing students' willingness to communicate. Cognitively, immediate, clear, and objective feedback helped students recognize both linguistic strengths and errors. Linguistically, real-time feedback promoted explicit awareness of tense inconsistencies and lexical misuse while encouraging students to monitor articulation and regulate speaking rate. Despite a technological constraint involving premature turn-taking caused by the AI misinterpreting cognitive pauses as the end of an utterance, students demonstrated digital agency by employing strategic conversational fillers to maintain interactional continuity. Thus, Gemini AI can serve as a low-pressure practice environment that bridges students' readiness toward real-world oral interaction.
ABSTRAK
Perkembangan kecerdasan buatan generatif dalam pembelajaran bahasa membuka peluang baru untuk menyediakan umpan balik lisan yang cepat dan personal, tetapi pemanfaatannya sebagai perancah digital dalam praktik komunikasi interaktif masih memerlukan kajian lebih lanjut. Penelitian ini bertujuan mengeksplorasi keterlibatan mahasiswa Program Studi Pendidikan Bahasa Inggris dengan umpan balik berbasis Kecerdasan Buatan (AI) generatif sebagai mekanisme perancah digital (digital scaffolding) selama praktik komunikasi lisan interaktif. Penelitian ini menggunakan studi kasus kualitatif yang melibatkan tiga mahasiswa EFL tingkat menengah di Institut Pendidikan Indonesia Garut, Jawa Barat. Data dikumpulkan melalui interaksi lisan dalam beberapa sesi dan wawancara retrospektif semi-terstruktur, kemudian dianalisis menggunakan analisis tematik enam tahap Braun dan Clarke. Penelitian ini menggunakan Teori Sosiokultural Vygotsky dan Hipotesis Noticing Schmidt sebagai landasan teoretis untuk memahami proses perancahan, kesadaran linguistik, dan perkembangan interaksi lisan mahasiswa. Hasil penelitian menunjukkan bahwa Gemini AI berfungsi sebagai perancah afektif dan kognitif dalam praktik berbicara. Secara afektif, interaksi dengan AI menciptakan ruang praktik dengan tingkat kecemasan yang lebih rendah dan minim tekanan sosial sehingga meningkatkan kesiapan mahasiswa untuk berkomunikasi. Secara kognitif, umpan balik yang cepat, jelas, dan objektif membantu mahasiswa mengenali kekuatan serta kesalahan penggunaan bahasa. Secara linguistik, umpan balik waktu nyata mendorong kesadaran terhadap ketidaktepatan tense dan penggunaan leksikal, sekaligus membantu mahasiswa memantau artikulasi dan mengatur kecepatan berbicara. Meskipun terdapat kendala berupa pemotongan giliran bicara akibat AI salah menginterpretasikan jeda berpikir sebagai akhir tuturan, mahasiswa menunjukkan agensi digital melalui penggunaan penanda percakapan strategis. Dengan demikian, Gemini AI dapat berfungsi sebagai ruang latihan bertekanan rendah yang menjembatani kesiapan mahasiswa menuju interaksi lisan di dunia nyata.
Downloads
References
Amoah, S., & Yeboah, J. (2021). The speaking difficulties of Chinese EFL learners and their motivation towards speaking the English language. Journal of Language and Linguistic Studies, 17(1), 56–69. https://doi.org/10.52462/jlls.4
Asad, M. M., Aftab, K., Sherwani, F., Churi, P., Moreno-Guerrero, A. J., & Pourshahian, B. (2021). Techno-pedagogical skills for 21st century digital classrooms: An extensive literature review. Education Research International, 2021, 1–12. https://doi.org/10.1155/2021/8160084
Burns, A. (2019). Concepts for teaching speaking in the English language classroom. LEARN Journal: Language Education and Acquisition Research Network, 12(1), 1–11. https://doi.org/10.3126/kvmrj.v6i1.84530
Chu, R. (2011). Effects of teacher's corrective feedback on accuracy in the oral English of English-majors college students. Theory and Practice in Language Studies, 1(5), 454–459. https://doi.org/10.4304/tpls.1.5.454-459
Davis, F. D., & Davis, F. (1989). Perceived usefulness, perceived ease of use, and user acceptance of information technology. MIS Quarterly, 13(3), 319–340. https://doi.org/10.2307/249008
Ellis, R. (2009). Corrective feedback and teacher development. L2 Journal, 1(1), 3–18. https://doi.org/10.5070/12.v1i1.9054
Etikan, I., Musa, S. A., & Alkassim, R. S. (2016). Comparison of convenience sampling and purposive sampling. American Journal of Theoretical and Applied Statistics, 5(1), 1–4. https://doi.org/10.11648/j.ajtas.20160501.11
Hou, X. L., He, S. Y., & Cui, G. R. X. (2024). Learner use of AI-generated feedback for written corrective feedback in L2 writing: Usefulness, user proficiency and attitude. ACM International Conference Proceeding Series, 70–76. https://doi.org/10.1145/3678726.3678767
Liang, J., Wang, L., Luo, J., Yan, Y., & Fan, C. (2023). The relationship between student interaction with generative artificial intelligence and learning achievement: Serial mediating roles of self-efficacy and cognitive engagement. Frontiers in Psychology, 14, 1285392. https://doi.org/10.3389/fpsyg.2023.1285392
Lim, W. M. (2025). What is qualitative research? An overview and guidelines. Australasian Marketing Journal, 33(1), 12–28. https://doi.org/10.1177/14413582241264619
Liu, H., & Feng, M. (2023). The role of learner engagement with corrective feedback in EFL/ESL classrooms. Frontiers in Psychology, 14, 1118467. https://doi.org/10.3389/fpsyg.2023.1118467
Nazaretsky, T., Mejia-Domenzain, P., Swamy, V., Frej, J., & Käser, T. (2024). AI or human? Evaluating student feedback perceptions in higher education. Lecture Notes in Computer Science, 15159, 284–298. https://doi.org/10.1007/978-3-031-72315-5_20
Newton, J. M. (2024). Stepping up the quality of English language teaching: How can Nation's four-strands principle help? VNU Journal of Foreign Studies, 40(3), 161–171. https://doi.org/10.63023/2525-2445/jfs.ulis.5201
Palinkas, L. A., Horwitz, S. M., Green, C. A., Wisdom, J. P., Duan, N., & Hoagwood, K. (2016). Purposeful sampling for qualitative data collection and analysis in mixed method implementation research. Administration and Policy in Mental Health and Mental Health Services Research, 42(5), 533–544. https://doi.org/10.1007/s10488-013-0528-y
S, K. (2024). Enhancing writing proficiency through AI-powered feedback: A quasi-experimental study using Google Gemini. LinguaEducare: Journal of English and Linguistic Studies, 1(2), 83–96. https://doi.org/10.63324/h6q1ak58
Tajik, A. (2025). Integrating AI-driven emotional intelligence in language learning platforms to improve English speaking skills through real-time adaptive feedback. Research Square, 1–41. https://doi.org/10.20944/preprints202501.2205.v1
Tondeur, J., Trevisan, O., Howard, S. K., & van Braak, J. (2025). Preparing preservice teachers to teach with digital technologies: An update of effective SQD-strategies. Computers & Education, 232, 105262. https://doi.org/10.1016/j.compedu.2025.105262
Wang, X., Liu, Q., Pang, H., Tan, S. C., Lei, J., Wallace, M. P., & Li, L. (2023). What matters in AI-supported learning: A study of human-AI interactions in language learning using cluster analysis and epistemic network analysis. Computers & Education, 194, 104703. https://doi.org/10.1016/j.compedu.2022.104703
Yaseen, H., Mohammad, A. S., Ashal, N., Abusaimeh, H., Ali, A., & Sharabati, A. A. A. (2025). The impact of adaptive learning technologies, personalized feedback, and interactive AI tools on student engagement: The moderating role of digital literacy. Sustainability, 17(3), 1133. https://doi.org/10.3390/su17031133
Zou, B., Du, Y., Wang, Z., & Chen, J. (2023). An investigation into artificial intelligence speech evaluation programs with automatic feedback for developing EFL learners' speaking skills. SAGE Open, 13(3), 1–14. https://doi.org/10.1177/21582440231193818
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Arda Arda, Anne Ratna Suminar, Yustika Nur Fajriah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
