Comparative Analysis of AI vs. Human Feedback Effects on IELTS Candidates' Writing Performance
سال انتشار: 1404
نوع سند: مقاله ژورنالی
زبان: انگلیسی
مشاهده: 121
فایل این مقاله در 24 صفحه با فرمت PDF قابل دریافت می باشد
- صدور گواهی نمایه سازی
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_EFL-10-1_002
تاریخ نمایه سازی: 11 شهریور 1404
چکیده مقاله:
This study compares the effectiveness of artificial intelligence (AI)-generated feedback (specifically using ChatGPT) and human feedback in improving the writing performance of B۲-level IELTS candidates. A mixed-methods approach was employed, combining quantitative and qualitative data to evaluate the impact of both types of feedback. A total of ۱۰۰ B۲-level English learners from various cities of Iran were selected through convenience sampling and then randomly assigned to two groups. Pre- and post-test assessments, using mock IELTS exams, provided quantitative data, while qualitative data were gathered through participant questionnaires. These findings reinforce the superiority of human feedback in enhancing higher-order writing skills; however, this study extends prior research by examining the effectiveness of AI-generated and human feedback within the specific context of Iranian IELTS candidates. Given the traditionally grammar-focused writing instruction in Iran, the results highlight the need for integrated feedback approaches that address coherence, cohesion, and argument development. The study also offers practical implications for IELTS preparation programs in non-native English-speaking countries, advocating for a structured combination of AI and human feedback to maximize writing proficiency. Learners valued the personalized guidance of human feedback, which fostered motivation and engagement. Conversely, AI-generated feedback excelled in correcting surface-level errors, such as grammar and vocabulary, offering immediacy and consistency. Nonetheless, AI's lack of interpretive depth limited its ability to address complex writing issues like argumentative development and cohesive flow. This study underscores the potential benefits of integrating AI and human feedback to enhance writing instruction for standardized assessments. Future research should investigate strategies to refine AI tools for better support of advanced writing skills.
کلیدواژه ها:
نویسندگان
علیرضا رمضانی
MA in TEFL, Department of English Language, Islamic Azad University, Zanjan Branch, Zanjan, Iran
هومن بیژنی
Assistant Professor of TEFL, Department of English Language, Islamic Azad University, Zanjan Branch, Zanjan, Iran
محمد رضا اروجی
Assistant Professor of TEFL, Department of English Language, Islamic Azad University, Zanjan Branch, Zanjan, Iran
مراجع و منابع این مقاله:
لیست زیر مراجع و منابع استفاده شده در این مقاله را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود مقاله لینک شده اند :