The growing adoption of artificial intelligence in educational assessment has created new opportunities for scalable, consistent, and data-driven evaluation of speaking skills. However, speaking assessment in teacher education remains largely dependent on manual expert scoring, which is time-consuming and susceptible to inter-rater variability. This study develops and validates an AI-integrated Learning Management System (LMS) module for automated assessment of communicative competence in pre-service English teachers. The proposed framework combines automatic speech recognition, acoustic and lexical feature extraction, interpretable regression-based predictive scoring, and a learning analytics dashboard within a modular LMS architecture. A controlled eight-week intervention was conducted with 64 participants randomly assigned to experimental and control groups. The results showed statistically significant post-intervention gains in the experimental group compared with the control condition, with a large effect size. Multivariate analysis further confirmed significant improvements across fluency, pronunciation, lexical richness, and interactivity. In addition, digital engagement indicators explained a substantial proportion of communicative competence growth, highlighting the importance of integrating automated scoring with learner analytics and feedback mechanisms. From a technical perspective, the system demonstrated strong alignment with expert ratings, low inference time, and substantial efficiency gains over traditional assessment procedures. The study contributes a deployable and reproducible applied AI solution that balances pedagogical relevance, predictive transparency, and institutional scalability, offering a practical framework for AI-driven speaking assessment in higher education.
P.-L. Chuang and X. Yan, “Language assessment in the era of generative artificial intelligence: Opportunities, challenges, and future directions,” System, vol. 114, art. no. 103846, 2025, [Online]. Available: https://doi.org/10.1016/j.system.2025.103846.
D. Alonzo, J. M. V. Abril, and C. Zin Oo, “The use of artificial intelligence in English language assessment: Empirical evidence and future directions,” Crit. Stud. Teach. Learn., vol. 13, no. 2, 2025, [Online]. Available: https://doi.org/10.14426/cristal.v13i2.2723.
W. Bao and F. D. Yusop, “Technology-enhanced second language willingness to communicate: A systematic review and proposed framework for effective language education,” Multidiscip. Rev., vol. 9, no. 4, art. no. 2026170, Sep. 2025, [Online]. Available: https://doi.org/10.31893/multirev.2026170.
M. Farrús and V. Navarro, “Automatic speech recognition for second language pronunciation feedback: Trends and developments,” Languages, vol. 8, no. 4, art. no. 242, 2023, [Online]. Available: https://doi.org/10.3390/languages8040242.
Y. Li, J. Kaur, and S. Johnson, “Automated scoring models for spoken performance: A comparative study,” IEEE Access, vol. 9, pp. 45123-45138, 2021, [Online]. Available: https://doi.org/10.1109/ACCESS.2021.3068412.
D. Gašević, S. Dawson, and G. Siemens, “Let’s not forget: Learning analytics are about learning,” TechTrends, vol. 63, pp. 591-597, 2020, [Online]. Available: https://doi.org/10.1007/s11528-019-00446-y.
A. Palanci, B. Stantic, and M. I. Chong, “Learning analytics in distance education: A systematic review,” Educ. Inf. Technol., vol. 29, pp. 3459-3482, 2024, [Online]. Available: https://doi.org/10.1007/s10639-024-12737-5.
S. Z. Salas-Pilco, “Artificial intelligence and learning analytics in teacher education,” Educ. Sci., vol. 12, no. 8, art. no. 569, 2022, [Online]. Available: https://doi.org/10.3390/educsci12080569.
C. Feng and L. Yang, “Interpretability and explainability in AI-based educational assessments: A critical review,” EDUCAUSE Rev., vol. 38, no. 1, pp. 45-61, 2025.
A. Khosravi, J. H. Spector, and M. Gašević, “Ethical design and use of learning analytics,” J. Learn. Anal., vol. 10, no. 2, pp. 1-17, 2023, [Online]. Available: https://doi.org/10.18608/jla.2023.10911.
B. L. Youngs, “Design principles for responsible AI in educational technology,” Educ. Technol. Res. Dev., vol. 70, pp. 1251-1270, 2025, [Online]. Available: https://doi.org/10.1007/s11423-024-09954-9.
R. Alfredo, V. Echeverria, Y. Jin, L. Yan, Z. Swiecki, D. Gašević, and R. Martinez-Maldonado, “Human-centred learning analytics and AI in education: A systematic literature review,” Comput. Educ. Artif. Intell., vol. 6, art. no. 100215, 2024, [Online]. Available: https://doi.org/10.1016/j.caeai.2024.100215.
S. Mamayoqubova and D. Begmatova, “Pedagogical conditions of developing professional competence of teachers of higher educational institutions,” BIO Web Conf., vol. 65, art. no. 10025, Jan. 2023, [Online]. Available: https://doi.org/10.1051/bioconf/20236510025.
