Amine Hatun Ataş
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Amine Hatun Ataş has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Behice Ceyda Cengiz
Zonguldak Bülent Ecevit University
3 shared publications - Berkan Celik
Van Yüzüncü Yil University
3 shared publications - Zahide Yildirim
Orta Doğu Teknik Üniversitesi
2 shared publications Bahar Shahrokhian
Arizona State University
1 shared publication- Conrad Borchers
Vanderbilt University
1 shared publication - Elham Tajik
University of Albany, Albany, New York, USA
1 shared publication
Latest Publications
- Top Cited Papers
Exploring second language writers’ engagement with ChatGPT feedback: Revision behaviors and perceptions
- 15 July 2025
- Published by Springer Nature
- p. 60-73
Comparing a Human’s and a Multi-Agent System’s Thematic Analysis: Assessing Qualitative Coding Consistency
- 15 July 2025
- Published by Springer Nature
- p. 60-73
Comparing a Human’s and a Multi-Agent System’s Thematic Analysis: Assessing Qualitative Coding Consistency
- Open Access
- 30 December 2024
- Published by Sakarya University Journal of Education in Sakarya University Journal of Education
- Vol. 14 (3) , 515-538
Evaluating ChatGPT in Generating Feedback on Content and Organization Components of EFL Compare and Contrast Essays
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.
- 30 December 2024
- Published by Sakarya University Journal of Education in Sakarya University Journal of Education
- Vol. 14 (3) , 515-538
Open AccessEvaluating ChatGPT in Generating Feedback on Content and Organization Components of EFL Compare and Contrast Essays
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.
- 26 September 2024
- Published by Springer Nature in Educational Technology Research and Development
- Vol. 73 (1) , 567-613
A shared metacognition-focused instructional design model for online collaborative learning environments
- 26 September 2024
- Published by Springer Nature in Educational Technology Research and Development
- Vol. 73 (1) , 567-613
A shared metacognition-focused instructional design model for online collaborative learning environments
- 29 April 2024
- Published by Taylor & Francis in Computer Assisted Language Learning
- Vol. 38 (4) , 951-986
Exploring the correlation and influential factors of online self-regulation and in-class co-regulation in a flipped EFL writing classroom
- 29 April 2024
- Published by Taylor & Francis in Computer Assisted Language Learning
- Vol. 38 (4) , 951-986
Exploring the correlation and influential factors of online self-regulation and in-class co-regulation in a flipped EFL writing classroom
- 30 September 2022
- Published by Journal of Educational Technology and Online Learning in Journal of Educational Technology and Online Learning
- Vol. 5 (3) , 585-599
Adaptation of the shared-metacognition questionnaire (SMQ) into Turkish for online collaborative learning environments
The aim of this study was to adapt Shared-Metacognition Questionnaire (SMQ) into Turkish. The original version of the SMQ consisting of 26 items and two factors measures metacognition in online collaborative learning environments based on the Community of Inquiry (CoI) framework. The data were collected from 364 university students who had online learning experience. Confirmatory factor analysis was done on two-factor and three-factor model. The three-factor model was confirmed with satisfactory model fit indices. The value of AVE for each dimension verified the convergent validity. For verifying discriminant validity, the AVE estimates of three factors were compared with the square of correlation among the factors, and reported as greater than shared-variance of related row-column values. The factor loading values indicated very good to excellent loadings, as verifying the statistically satisfactory indicator reliability. For internal consistency, composite reliability and alpha reliability were found satisfactory. Thus, the Turkish version of the SMQ indicated a reliable and valid estimate for online collaborative learning environments. Moreover, an Independent Samples t-Test was performed to examine whether there is a significant mean difference between female and male groups, and revealed that females scored higher on total shared metacognition, individual monitoring, individual regulation and group regulation than males.
- 30 September 2022
- Published by Journal of Educational Technology and Online Learning in Journal of Educational Technology and Online Learning
- Vol. 5 (3) , 585-599
Adaptation of the shared-metacognition questionnaire (SMQ) into Turkish for online collaborative learning environments
The aim of this study was to adapt Shared-Metacognition Questionnaire (SMQ) into Turkish. The original version of the SMQ consisting of 26 items and two factors measures metacognition in online collaborative learning environments based on the Community of Inquiry (CoI) framework. The data were collected from 364 university students who had online learning experience. Confirmatory factor analysis was done on two-factor and three-factor model. The three-factor model was confirmed with satisfactory model fit indices. The value of AVE for each dimension verified the convergent validity. For verifying discriminant validity, the AVE estimates of three factors were compared with the square of correlation among the factors, and reported as greater than shared-variance of related row-column values. The factor loading values indicated very good to excellent loadings, as verifying the statistically satisfactory indicator reliability. For internal consistency, composite reliability and alpha reliability were found satisfactory. Thus, the Turkish version of the SMQ indicated a reliable and valid estimate for online collaborative learning environments. Moreover, an Independent Samples t-Test was performed to examine whether there is a significant mean difference between female and male groups, and revealed that females scored higher on total shared metacognition, individual monitoring, individual regulation and group regulation than males.
- 19 February 2017
- Published by Taylor & Francis in Interactive Learning Environments
- Vol. 26 (1) , 75-90
A question–answer system for mobile devices in lecture-based instruction: a qualitative analysis of student engagement and learning
The aim of this study was to explore the opinions, perceptions and evaluations of students about their experiences with a question–answer system used on mobile devices in a lecture-based course. Basic qualitative research method was employed in this study to understand how students made sense of their experiences during the instruction. The participants of the study were 25 of 42 students enrolled in a Computer Hardware course, who were interviewed in five sessions of focus-groups. Data analysis was done based on the six steps of inductive analysis. The results showed that students mostly ascribed the meaning of their engagement to the observable behaviors about academic challenge. Concerning inhibiting factors for participating in a lecture, they stressed the constraints of lecture method. As inhibiting factors for asking questions, they mostly stated shyness as a reason. The results of the research were discussed reflectively to investigate the constructed meanings of participants about the context and to make suggestions for further studies.
- 19 February 2017
- Published by Taylor & Francis in Interactive Learning Environments
- Vol. 26 (1) , 75-90
A question–answer system for mobile devices in lecture-based instruction: a qualitative analysis of student engagement and learning
The aim of this study was to explore the opinions, perceptions and evaluations of students about their experiences with a question–answer system used on mobile devices in a lecture-based course. Basic qualitative research method was employed in this study to understand how students made sense of their experiences during the instruction. The participants of the study were 25 of 42 students enrolled in a Computer Hardware course, who were interviewed in five sessions of focus-groups. Data analysis was done based on the six steps of inductive analysis. The results showed that students mostly ascribed the meaning of their engagement to the observable behaviors about academic challenge. Concerning inhibiting factors for participating in a lecture, they stressed the constraints of lecture method. As inhibiting factors for asking questions, they mostly stated shyness as a reason. The results of the research were discussed reflectively to investigate the constructed meanings of participants about the context and to make suggestions for further studies.