Human and AI-generated feedback in higher education: A systematic review of effectiveness and student perceptions
Authors:
- Candy Haydee Guardia-PaniuraCGCandy Haydee Guardia-Paniura
- Timoteo Cueva-LuzaTCTimoteo Cueva-Luza
- Favio Mauricio Cruz-CarpioFCFavio Mauricio Cruz-Carpio
- Raúl Reynaldo Ito-DíazRIRaúl Reynaldo Ito-Díaz
- David Victor Apaza-PacoDADavid Victor Apaza-Paco
- Nilda Rosas-RojasNRNilda Rosas-Rojas
- Benedicta Mamani-MamaniBMBenedicta Mamani-Mamani
- Ángel Terrero-PérezÁTÁngel Terrero-Pérez
- Renato Yassutaka Faria YaedúRYRenato Yassutaka Faria Yaedú
- Mariela Peralta-MamaniMPMariela Peralta-Mamani
Top Cited Papers
Open Access
- 4 February 2026
- journal article
- review article
- Published by Bastas Publications in Contemporary Educational Technology
- Vol. 18 (1) , ep623
Abstract
This study aims to compare the feedback provided by human professors and ChatGPT on university students’ work and to report on students’ perceptions of both types of feedback. A systematic review was conducted following PRISMA 2020 guidelines. Databases research included Web of Science, Scopus, EBSCO, ACM Digital Library, and IEEE Xplore, with additional gray literature sources, until October 2024. Inclusion criteria were cross-sectional studies evaluating university students’ work, comparing feedback from ChatGPT with human professors. Data extraction was performed using a standardized form, and risk of bias was assessed with the Joanna Briggs Institute critical appraisal tool. A narrative synthesis of the results was made. PROSPERO registration number: CRD42024566691. This review included 8 studies with 461 students. ChatGPT feedback was detailed and rapid, while human feedback was valued for its personalization and emotional support. Students appreciated the detailed and immediate nature of ChatGPT feedback but noted its lack of emotional nuance and context-specific guidance. Human feedback was preferred for addressing individual learning needs and providing affective support. A combination of both types of feedback to maximize benefits. ChatGPT can assist human teachers by providing detailed and timely feedback to university students. However, human supervision is essential to ensure feedback is nuanced and contextually appropriate. A hybrid approach can optimize the learning experience in higher education. Further research is necessary to explore AI applications in educational settings and understand their impact on learning outcomes.Keywords
This publication has 27 references indexed in Scilit:
- The future of grading programming assignments in education: The role of ChatGPT in automating the assessment and feedback processThinking Skills and Creativity, 2024
- Students’ Experiences of Using ChatGPT in an Undergraduate Programming CourseIEEE Access, 2024
- Exploring the impact of ChatGPT-generated feedback on technical writing skills of computing students: A blinded studyEducation and Information Technologies, 2024
- Feedback seeking abilities of L2 writers using ChatGPT: a mixed method multiple case studyKybernetes, 2024
- Student Perceptions of ChatGPT Use in a College Essay Assignment: Implications for Learning, Grading, and Trust in Artificial IntelligenceIEEE Transactions on Learning Technologies, 2024
- Can ChatGPT effectively complement teacher assessment of undergraduate students’ academic writing?Assessment & Evaluation in Higher Education, 2024
- ChatGPT's capabilities in providing feedback on undergraduate students’ argumentation: A case studyThinking Skills and Creativity, 2023
- To resist it or to embrace it? Examining ChatGPT’s potential to support teacher feedback in EFL writingEducation and Information Technologies, 2023
- Can Large Language Models Provide Feedback to Students? A Case Study on ChatGPT2023
- The Janus face of artificial intelligence feedback: Deployment versus disclosure effects on employee performanceStrategic Management Journal, 2021