Earticle

초록

영어

This study examines how written language shapes the use of a free AI-powered image-generation tool by language learners in processes of writing and meaning-making, and how such image-supported interaction affects learners’ writing performance. To evaluate the potential benefits of image utilization in language learning, DALL·E 3 was employed via the free version of ChatGPT 4.5. The participants were sixty lowproficiency Korean EFL college students enrolled in a general writing course, who were divided into two groups: Group A, comprising beginner and elementary learners (CEFR A1–A2), and Group B, made up of lower-intermediate learners (CEFR B1). The study draws on sentiment analysis of learners’ responses to image use, conducted in Python using a Hugging Face transformer model. The resulting sentiment scores were compared with learners’ Likert-scale ratings, and pre- and post-test writing performance was measured separately. The findings provide an integrated account of how images and AI support shaped both affective responses and measurable gains in EFL writing, although more for Group B than for Group A learners.

목차

Abstract
1. INTRODUCTION
1.1 Background of the Study
1.2 Rationale the Study
2. METHODS
2.1 Participants
2.2 Data Collection and Analysis
3. RESULTS
3.1 Writing Performance Impact
3.2 Perceptions of and Satisfaction with Using DALL·E 3
4. DISCUSSION
5. CONCLUSION
ACKNOWLEDGEMENT
REFERENCES

키워드

저자

• SoHee Kim [ Research Professor, Center for English Language Education, Korea Univ, Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Advanced Culture Technology(IJACT)

• 간기

  계간

• pISSN

  2288-7202

• eISSN

  2288-7318

• 수록기간

  2013~2025

• 등재여부

  KCI 등재

• 십진분류

  KDC 600 DDC 700