Informasi Publikasi

Nama Jurnal / Penerbit
Linguistics and English Language Teaching Journal Muhammadiyah Mataram
Tahun Publikasi
2026
Penerbit
Universitas Muhammadiyah Mataram
DOI
https://doi.org/10.31764/leltj.v14i1.39801
Volume / Nomor
Vol. 14 No. 1
Halaman
53-64
Jenis Publikasi
jurnal
Kategori Skor LP2M
NAS Jurnal Nasional

Penulis

Lalu Isnaeni Rahman, Pathul Indriana, Riris Sugianto

Kata Kunci

Deep Learning Approach Speaking Ability EFL Classroom AI-Assisted Learning English Language Teaching

Abstrak

English speaking skill is very crucial because this ability enables students
to express thoughts, feelings, and ideas in real situations through a dynamic
and interactive process for academic and professional purposes. Despite
the growing integration of AI-based language learning approaches in EFL
classrooms, there is still limited empirical evidence on the effectiveness of
deep learning-oriented instruction in improving students’ speaking ability.
The purpose of this study was to investigate the effect of the deep learning
approach on the speaking ability of first-semester students at the Faculty
of Information and Communication Technology, Universitas Teknologi
Mataram. The study employed a quasi-experimental design with a pre-test
and post-test control group involving 60 students. The sample was 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 higher improvement in
speaking ability than 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.


Artikel Lengkap

Baca artikel lengkap dalam format PDF.