A systematic review of AI-based feedback in educational settings

Hatice Yildiz Durak () and Aytuğ Onan ()
Additional contact information
Hatice Yildiz Durak: Necmettin Erbakan University
Aytuğ Onan: Software Engineering, Izmir Katip Celebi University

Journal of Computational Social Science, 2025, vol. 8, issue 4, No 15, 40 pages

Abstract: Abstract Artificial intelligence (AI) technologies have been an important milestone in feedback applications in education. To identify and guide the effective use of AI in educational settings, it is necessary to examine research trends with a holistic approach. In addition, it is also important to analyze the feedback design and its effects on the learning process in studies applying AI-based feedback approaches. Based on all these situations, this study aims to conduct a systematic literature review with studies involving AI-based feedback applications. In the study, 953 publications indexed in the Web of Science (WoS) SSCI database between 2014 and 2024 were listed. After applying inclusion and exclusion criteria, 91 articles were included in the final analysis. The descriptive results indicate a significant increase in the number of publications over the past two years, with the majority of articles appearing in the journal Education and Information Technologies. Experimental methodologies were identified as the most frequently employed approaches. The most prevalent participant group was identified as university students. The findings suggest that AI-based feedback systems have considerable potential to deliver real-time feedback that is tailored and personalised to meet individual students’ needs. The utilisation of AI-based feedback systems has been demonstrated to enhance various aspects of learning, including motivation, attitude, self-regulation, self-efficacy, and autonomy. Furthermore, they facilitate teacher-student interactions and have the potential to strengthen collaborative learning processes. However, despite the benefits offered by AI-based feedback systems in education, several challenges and risks persist, including insufficient contextual sensitivity, algorithmic bias, overreliance on technology, and a possible decline in teacher-student interactions. A critical review of the extant literature identified significant gaps, including the need for effective feedback systems designed for diverse age and cultural groups, as well as the creation of personalised feedback models informed by emotional analysis. On the other hand, the reviewed studies reported that the use of hybrid models has the potential to further increase the effectiveness of AI-based feedback systems.

Keywords: Systematic review; Feedback; Artificial intelligence-based feedback (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-025-00428-1 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:8:y:2025:i:4:d:10.1007_s42001-025-00428-1

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-025-00428-1

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().