Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal DUTIES: Education and Humanities International Journal Journal of Modern Approaches to Communication, Humanities, and Academia
Zahratun Nufus
STAI Rasyidiyah Khalidiyah (Rakha) Amuntai
Humanities Education Languange, Linguistic, Communication & Media Mathematics Social Sciences Other

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

Found 2 Documents
Search

 1 
ChatGPT's Handling of L2 Learners’ Fossilized Errors: A Linguistic Evaluation Zahratun Nufus; Saleman Mashood Warrah
DUTIES: Education and Humanities International Journal Vol. 1 No. 2 (2025): DUTIES: Education and Humanities International Journal
Publisher : CV. Akademi Merdeka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70152/duties.v1i2.219

Abstract

This study investigates ChatGPT’s capacity to address fossilized grammatical errors in English as a Foreign Language (EFL) learners’ academic writing. Through a mixed-methods design, a controlled corpus of 500 hypothetical sentences containing persistent error types, such as verb tenses, articles, prepositions, and non-idiomatic expressions, was submitted to ChatGPT-4. Quantitative analysis evaluated correction accuracy using standard metrics (precision, recall, F-score), while qualitative content analysis assessed the pedagogical appropriateness and consistency of ChatGPT’s feedback. Results showed high accuracy in correcting rule-based structures (e.g., subject-verb agreement), but significantly lower performance for context-sensitive and fossilized errors. While ChatGPT often provided clear corrections, its feedback frequently lacked explanatory depth, contextual sensitivity, and scaffolding necessary for promoting learner noticing and long-term acquisition. These findings suggest that although ChatGPT can effectively support surface-level proofreading, it cannot fully substitute the role of human instructors in addressing deeply ingrained L2 errors. The study emphasizes the importance of explainable AI, AI literacy, and hybrid instructional models that combine technological efficiency with pedagogical intentionality. It offers implications for educators, curriculum developers, and AI tool designers seeking to integrate language models into second language acquisition contexts.
Voices in Transition: EFL Learners’ Interaction with AI Tools to Improve Speaking Zahratun Nufus; Pooveneswaran Nadarajan
MATCHA: Journal of Modern Approaches to Communication, Humanities, and Academia Vol. 1 No. 2 (2025): MATCHA: Journal of Modern Approaches to Communication, Humanities, and Academia
Publisher : CV. Akademi Merdeka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70152/matcha.v1i2.208

Abstract

This study explores how English as a Foreign Language (EFL) learners experience and make sense of their interactions with Artificial Intelligence (AI) tools to develop speaking proficiency. Using a narrative inquiry approach, in-depth interviews and reflective journals were collected from 12 learners who regularly used ChatGPT, ELSA Speak, Duolingo, and MySpeaker Rhetorich. Grounded in Sociocultural Theory and Swain’s Output Hypothesis, the analysis examined how AI mediated learners’ cognitive and affective engagement within their Zones of Proximal Development. Findings revealed that AI tools created psychologically safe spaces, reduced speaking anxiety, and provided immediate, precise feedback, fostering greater fluency, accuracy, and learner autonomy. Learners valued AI’s personalization and accessibility but also noted limitations in cultural nuance, humor, and emotional depth, positioning AI as a supplement rather than a substitute for human interaction. This study offers qualitative insights into the affective and social dimensions of AI-mediated speaking practice, highlighting strategies for integrating AI into EFL pedagogy to support both linguistic development and emotional readiness for communication.
Co-Authors Pooveneswaran Nadarajan Saleman Mashood Warrah