Browsing by Author "Cengiz, Behice Ceyda"

Now showing 1 - 2 of 2

Evaluating Chatgpt in Generating Feedback on Content and Organization Components of Efl Compare and Contrast Essays
(2024) Atas, Amine Hatun; Cengiz, Behice Ceyda; Celik, Berkan
ChatGPT, an innovative large language model that has impressed worldwide audiences with its exceptional generative capabilities, is now positioned to significantly transform the field of education. The purpose of this exploratory study is to investigate how accurately ChatGPT generates feedback on the content and organization components of EFL compare and contrast essays and the extent to which the feedback length provided by ChatGPT differs from that of the human teacher.To address these questions, a ChatGPT prompt incorporating evaluation criteria for content and organization components was developed, generating feedback on 10 compare and contrast student essays using the ChatGPT 3.5 version. The ChatGPT feedback and teacher feedback were assessed quantitatively and qualitatively according to the predetermined evaluation criteria. Furthermore, two types of feedback were compared descriptively and by conducting the Wilcoxon Sign Rank Test. The findings revealed that ChatGPT produced highly accurate feedback for both content and organization components, surpassing the teacher in the length of feedback provided. While the accuracy rate of the generated feedback was high, issues such as holistic assessment of the essay, false positives, failure to provide feedback where needed, and discrepancies in the depth of feedback compared to teacher feedback were identified. The results suggest that while ChatGPT shows promise in providing educational feedback, teacher-AI collaboration in giving feedback for EFL compare and contrast essays is important for delivering feedback that optimally benefits learners.
Exploring Second Language Writers’ Engagement With ChatGPT Feedback: Revision Behaviors and Perceptions
(Elsevier Ltd, 2025) Cengiz, Behice Ceyda; Bilki, Zeynep; Ataş, Amine Hatun; Çelik, Berkan
While recent research underlines ChatGPT's potential as a second language (L2) writing feedback tool, its effectiveness and role in engaging L2 writers require further investigation. This study explores how English as a Foreign Language (EFL) writers engage with ChatGPT feedback by analyzing their revision behaviors and perceptions of its effectiveness in revising their opinion essays. Using a convergent parallel mixed methods design, the study involved 25 B1-level EFL students from a university in Türkiye. Data were collected through essay drafts, change tracker sheets, a questionnaire, and interviews. The descriptive and thematic analysis of essays, change tracker sheets, and interviews revealed that most content and language feedback was accepted, while organization feedback received mixed engagement of acceptance and rejection. Students were more likely to accept language use feedback than content or organization feedback, often incorporating ChatGPT's revisions directly. For content feedback, the most common revision operations were additions and substitutions while more than a third of the revisions in response to organization feedback involved no corrections. Correction was the most frequent revision operation for language use feedback. Questionnaire and interview analyses further revealed that while ChatGPT feedback was generally well-received and considered beneficial for writing improvement, students faced challenges related to feedback length, specificity, advanced language, and misunderstandings. This study provides valuable insights into how EFL students interact with ChatGPT-generated feedback, highlighting both its potential to support L2 writing development and the challenges that may limit its effectiveness. © 2025 Elsevier B.V., All rights reserved.