Mitigating Foreign Language Speaking Anxiety: The Impact of a Self-Hosted AI Voice Chatbot in the Libyan EFL Context
Jraba Street, Tripoli 0021, Libya
PDF

Keywords

AI-assisted language learning
EFL learners
Foreign Language Speaking Anxiety
Libya, voice chatbot
Affective Filter Hypothesis

Categories

How to Cite

Benarose, A., & Hmouma, M. (2026). Mitigating Foreign Language Speaking Anxiety: The Impact of a Self-Hosted AI Voice Chatbot in the Libyan EFL Context. International Journal of Peer-Reviewed Multidisciplinary Research, 2(1), 79-89. https://ijprmr.com/index.php/ijprmr/article/view/16

Abstract

This study is grounded in Krashen's Affective Filter Hypothesis, and it investigates how interactive and AI environments mitigate Foreign Language Speaking Anxiety (FLSA). While prior research has extensively explored commercial AI platforms, a critical empirical gap exists regarding researcher-developed self-hosted AI chatbots in high-anxiety EFL contexts. This study addresses this gap by analyzing the pedagogical impact of a localized AI tool at one University. A quasi-experimental design was adopted with a sample of N = 45 EFL learners (experimental group n = 25; control group n = 20). The intervention employed a self-hosted AI voice chatbot based on GPT-4o-realtime-preview API. It is designed as an oral production environment, while the control group received traditional classroom instruction. Data were collected using the Foreign Language Speaking Anxiety Scale, and they were analyzed using independent-samples t-tests. The results revealed a significant reduction in anxiety levels for the experimental group (p < .001), with a large effect size (Cohen's d = 1.48). Post-test scores for the experimental group decreased significantly (M = 2.61, SD = 0.38) compared to the control group (M = 3.28, SD = 0.41), t(43) = 7.89. The participants demonstrated enhanced linguistic confidence and a 30–38% reduction in avoidance behaviors, suggesting an increased willingness to communicate in peer and classroom interactions. These findings indicate that localized AI-driven conversational agents provide a "psychological safety net" that fosters risk-taking and learner autonomy. This study offers empirical evidence that adapted AI tools as viable pedagogical instruments for overcoming psychological barriers in restrictive EFL settings.

PDF

References

Alkarkhi, S. I., & Hmouma, M. A. A. (2025). The effects of well-being, resilience, work environment and job satisfaction on foreign language teaching enjoyment in Libyan context. IOSR Journal of Humanities and Social Science (IOSR-JHSS), 30(11), 49–68. https://doi.org/10.9790/0837-3011034968

Chen, L., Chen, P., & Lin, Z. (2020). Artificial intelligence in education: A review. IEEE Access, 8, 75264–75278. https://doi.org/10.1109/ACCESS.2020.2988510

Chen, X., Zou, D., Cheng, G., & Xie, H. (2023). Artificial intelligence-supported language learning: A systematic review of research from 2010 to 2022. Computers and Education: Artificial Intelligence, 4, Article 100127. https://doi.org/10.1016/j.caeai.2023.100127

Dizon, G. (2022). The effectiveness of AI chatbots in language learning: A systematic review. Computer Assisted Language Learning Electronic Journal, 23(1), 1–22.

Dizon, G., & Gayed, J. M. (2021). Examining the impact of AI chatbot interaction on EFL learners' willingness to communicate. Computer Assisted Language Learning Electronic Journal, 22(3), 1–16.

Dörnyei, Z., & Al-Hoorie, A. H. (2022). The motivational foundation of learning languages in the digital age. Multilingual Matters.

Fryer, L., & Nakao, K. (2021). Chatbots for language learning: Investigating learning outcomes and learner perceptions. ReCALL, 33(1), 1–19. https://doi.org/10.1017/S095834402000021X

Horwitz, E. K., Horwitz, M. B., & Cope, J. (1986). Foreign language classroom anxiety. The Modern Language Journal, 70(2), 125–132. https://doi.org/10.1111/j.1540-4781.1986.tb05256.x

Huang, J., Hew, K. F., & Fryer, L. (2022). Chatbots for language learning: A review of recent developments and future directions. Educational Technology & Society, 25(1), 1–15.

Huang, R., Spector, J. M., & Yang, J. (2021). Educational technology and artificial intelligence: Opportunities and challenges for language learning. Educational Technology Research and Development, 69(1), 1–6. https://doi.org/10.1007/s11423-021-09966-5

Krashen, S. D. (1982). Principles and practice in second language acquisition. Pergamon Press.

Liu, M. (2021). Foreign language anxiety and willingness to communicate in EFL classrooms. System, 96, Article 102402. https://doi.org/10.1016/j.system.2020.102402 Hmouma, M., & Benarose, A. (2026). The Effectiveness of Using Artificial Intelligence on Learning Vocabulary among Libyan EFL University Undergraduates at Zawia University. International Journal of Peer-Reviewed Multidisciplinary Research, 2(1), 12-18. https://ijprmr.com/index.php/ijprmr/article/view/10

Plonsky, L., & Oswald, F. L. (2020). How big is “big”? Interpreting effect sizes in L2 research. Language Learning, 70(4), 878–912. https://doi.org/10.1111/lang.12426

Teimouri, Y., Goetze, J., & Plonsky, L. (2022). Second language anxiety and achievement: A meta-analysis. Studies in Second Language Acquisition, 44(2), 363–387. https://doi.org/10.1017/S0272263121000311

Zawacki-Richter, O., Marín, V. I., Bond, M., & Gouverneur, F. (2022). Systematic review of research on artificial intelligence applications in higher education. International Journal of Educational Technology in Higher Education, 19(1), Article 23. https://doi.org/10.1186/s41239-022-00326-4 Sadighi, F., & Dastpak, M. (2017). The Sources of Foreign Language Speaking Anxiety of Iranian English Language Learners. International Journal of Education and Literacy Studies, 5(4), 111-115.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2026 Abdusalam Benarose, Mohamed Hmouma (Author)

Downloads

Download data is not yet available.