<![CDATA[This study investigated the effect of the deep learning approach on students’ speaking ability in an English as a Foreign Language (EFL) classroom. The study employed a quasi-experimental design with a pre-test and post-test control group design involving 60 first-semester students of the Faculty of Information and Communication Technology. The students were divided into two groups: an experimental group receiving deep learning-oriented and AI-assisted speaking instruction, and a control group receiving conventional speaking instruction. The instruments used in this study were speaking pre-tests and post-tests assessed based on fluency, pronunciation, vocabulary, grammar, and coherence. The collected data were analyzed using descriptive statistics, normality and homogeneity tests, paired sample t-tests, and independent sample t-tests through SPSS. The findings revealed that the experimental group achieved a significantly higher improvement in speaking ability compared to the control group. The post-test mean score of the experimental group increased from 61.20 to 78.90, while the control group improved from 60.85 to 69.40. The independent samples t-test showed a significance value of 0.000 (< 0.05), indicating that the deep learning approach had a statistically significant effect on students’ speaking ability. The results suggest that deep learning-oriented instruction integrated with collaborative tasks, project-based learning, and AI-assisted feedback can effectively enhance students’ speaking fluency, confidence, and engagement in EFL classrooms.]]>
Copyrights © 2026
