Jihan Fakhira
Universitas Muhammadiyah Prof. DR. HAMKA

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

AI SPEECH RECOGNITION IN HIGH-SCHOOL EFL SPEAKING ASSESSMENT: EFFECTIVENESS, MEANINGFULNESS, ENJOYMENT Namira Amaliah Putri; Siti Zulaiha; Herri Mulyono; Jihan Fakhira
Indonesian EFL Journal Vol. 12 No. 2 (2026)
Publisher : University of Kuningan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ieflj.v12i2.67

Abstract

This mixed-methods study examined the use of an AI-powered automatic speech recognition (ASR) tool (SpeechAce) for high-school EFL speaking assessment, with a focus on perceived effectiveness, meaningfulness, and enjoyment. Thirty students completed pre- and post-surveys, and ten students participated in semi-structured interviews; classroom observations were documented using a structured checklist. The intervention lasted two weeks (four 40-minute meetings) in which students accessed SpeechAce on their smartphones via the web and followed an iterative speak–check–revise routine. Quantitative results (paired-samples t-tests) showed significant gains in perceived speaking skill and meaningfulness, whereas enjoyment remained stable. Qualitative findings indicated that automated, non-judgmental feedback supported lower anxiety, increased willingness to speak, and greater learner autonomy, while teacher facilitation (warm-ups, modelling, and brief mini-lessons) helped students interpret feedback and set revision goals. These findings suggest that ASR-supported assessment can function as a formative learning episode in school contexts when tasks, feedback interpretation, and revision opportunities are explicitly structured.
Ginger writer feedback in English writing assessment: Association with motivation and self-confidence among Indonesian secondary students Anissa; Siti Zulaiha; Herri Mulyono; Jihan Fakhira
JOALL (Journal of Applied Linguistics and Literature) Vol. 11 No. 1 (2026): February, 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/joall.v11i1.44945

Abstract

Limited evidence exists on how platform-specific AI feedback functions in secondary EFL writing assessment—especially regarding its connections to learners’ motivation and self-confidence. This mixed-methods study used a one-group pre–post design with 35 Indonesian secondary EFL students during regular classes, integrating Ginger Writer. Motivation items were adapted from Schmidt & Watanabe, and self-confidence items from Bandura; both scales used 5-point Likert responses and showed good internal consistency. Semi-structured interviews, focus group discussions, and non-participant observations explored students’ experiences with AI feedback during drafting and revision. Quantitatively, motivation increased significantly (pre: M=20.9, post: M=22.1; t(34)=−2.32, p=.026, Cohen’s d₍z₎≈0.39), while self-confidence rose modestly but not significantly (pre: M=20.7, post: M=21.5; t(34)=−1.80, p=.081, d₍z₎≈0.30). Qualitative data showed students describing immediate, non-judgmental feedback that supported iterative revision, error noticing, and sustained effort, along with limitations such as connectivity issues and the need for teacher mediation to interpret suggestions. Triangulation suggests that quick, actionable feedback is linked to increased motivation during revision cycles, whereas confidence may require more extended exposure and scaffolding. The study indicates that schools can feasibly incorporate platform-specific AI feedback into formative writing assessment when combined with teacher guidance and reliable access; policy should support teacher professional development and infrastructure to enable equitable implementation.