Comparison of AI‐Generated and Instructor Feedback: No Significant Difference in Perceived Feedback Quality and Neither on Performance.
Background: Feedback is an essential part of the educational process as it enriches students' learning experiences, provides information about their current performance, shows them what is lacking in achieving goals, and provides guidance on the strategies needed to achieve those goals. Teachers, es...
| Publicado en: | Journal of Computer Assisted Learning Vol. 41; no. 5; pp. 1 - 12 |
|---|---|
| Autores principales: | , , |
| Formato: | research tables/charts randomized controlled trial Journal Article |
| Publicado: |
Wiley-Blackwell
Oct2025
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=188234229&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 188234229 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 02664909 6M1 jtl: Journal of Computer Assisted Learning issn: 02664909 maglogo: Y pubinfo: dt: Oct2025 vid: 41 iid: 5 pid: 480 pub: Wiley-Blackwell place: Malden, Massachusetts artinfo: ui: 188234229 188234229 188234229 10.1111/jcal.70134 188234229 ppf: 1 ppct: 11 formats: tig: atl: Comparison of AI‐Generated and Instructor Feedback: No Significant Difference in Perceived Feedback Quality and Neither on Performance. aug: au: Çağlar‐Özhan, Şeyma Tekeli, Perihan Arkün‐Kocadere, Selay affil: Department of Computer Technologies and Information Systems, Bartın University, Bartın, Türkiye sug: subj: Artificial Intelligence, Generative Feedback Students Learning Educational Technology Computer-Assisted Instruction Outcomes of Education Human Female Male Young Adult Randomized Controlled Trials Random Assignment Comparative Studies Experimental Studies Descriptive Statistics Academic Medical Centers Task Performance and Analysis Scales Perception Summated Rating Scaling kappa Statistic Pearson's Correlation Coefficient Mann-Whitney U Test Nonparametric Statistics Educational Measurement Course Evaluation Female Male ab: Background: Feedback is an essential part of the educational process as it enriches students' learning experiences, provides information about their current performance, shows them what is lacking in achieving goals, and provides guidance on the strategies needed to achieve those goals. Teachers, especially in crowded classrooms, often have difficulty allocating enough time to provide feedback. ChatGPT has the potential to deliver feedback more efficiently and effectively. Objective: This study aims to investigate the effectiveness of ChatGPT‐generated feedback in students' project proposal development process. Therefore, ChatGPT‐generated and instructor's feedback are compared in terms of perceived feedback quality and performance of students. Method: In the study, a post‐test control group experimental design was used. A total of 48 students enrolled in a blended course at a state university participated in the study for 6 weeks. The study was conducted using a randomised post‐test‐only control group experimental design. Students were asked to prepare a project proposal and feedback was given on each task. While the control group received instructor feedback, the experimental group received ChatGPT feedback. Data were collected via the Formative Feedback Perceptions Scale, and the students' project proposals were graded based on the rubric to evaluate their performance. Results and Conclusion: According to the Mann–Whitney U test analysis, there was no statistically significant difference between the experimental and the control group regarding both students' perceived feedback quality and performance. In conclusion, it can be argued that when guided by the appropriate prompts and asked to examine assignments of similar complexity to those in this study, ChatGPT can provide feedback of similar quality and equivalence to the feedback provided by instructors. In this way, it seems possible to improve students' learning as much as an instructor with individualised feedback by ChatGPT. Finally, it should be noted that these findings are within the limitations of the specific context of project proposal development, reliance on self‐reported data, and the experimental nature of the study; it is recommended to evaluate the effectiveness of AI‐generated feedback in different contexts. pubtype: Academic Journal doctype: research tables/charts randomized controlled trial Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|