Enhancing peer assessment with artificial intelligence
Abstract This paper surveys research and practice on enhancing peer assessment with artificial intelligence. Its objectives are to give the structure of the theoretical framework underpinning the study, synopsize a scoping review of the literature that illustrates this structure, and provide a case...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | International Journal of Educational Technology in Higher Education |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41239-024-00501-1 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832585540179853312 |
|---|---|
| author | Keith J. Topping Ed Gehringer Hassan Khosravi Srilekha Gudipati Kaushik Jadhav Surya Susarla |
| author_facet | Keith J. Topping Ed Gehringer Hassan Khosravi Srilekha Gudipati Kaushik Jadhav Surya Susarla |
| author_sort | Keith J. Topping |
| collection | DOAJ |
| description | Abstract This paper surveys research and practice on enhancing peer assessment with artificial intelligence. Its objectives are to give the structure of the theoretical framework underpinning the study, synopsize a scoping review of the literature that illustrates this structure, and provide a case study which further illustrates this structure. The theoretical framework has six areas: (i) Assigning Peer Assessors, (ii) Enhancing Individual Reviews, (iii) Deriving Peer Grades/Feedback, (iv) Analyzing Student Feedback, (v) Facilitating Instructor Oversight and (vi) Peer Assessment Systems. The vast majority of the 79 papers in the review found that artificial intelligence improved peer assessment. However, the focus of many papers was on diversity in grades and feedback, fuzzy logic and the analysis of feedback with a view to equalizing its quality. Relatively few papers focused on automated assignment, automated assessment, calibration, teamwork effectiveness and automated feedback and these merit further research. This picture suggests AI is making inroads into peer assessment, but there is still a considerable way to go, particularly in the under-researched areas. The paper incorporates a case study of the RIPPLE peer-assessment tool, which harnesses student wisdom, insights from the learning sciences and AI to enable time-constrained educators to immerse their students in deep and personalized learning experiences that effectively prepare them to serve as assessors. Once trained, they use a comprehensive rubric to vet learning resources submitted by other students. They thereby create pools of high-quality learning resources which can be used to recommend personalized content to students. RIPPLE engages students in a trio of intertwined activities: creation, review and personalized practice, generating many resource types. AI-driven real-time feedback is given but students are counseled to assess whether it is accurate. Affordances and challenges for researchers and practitioners were identified. |
| format | Article |
| id | doaj-art-fdd4d405900e43b28613921399ab9d95 |
| institution | Kabale University |
| issn | 2365-9440 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | International Journal of Educational Technology in Higher Education |
| spelling | doaj-art-fdd4d405900e43b28613921399ab9d952025-01-26T12:47:28ZengSpringerOpenInternational Journal of Educational Technology in Higher Education2365-94402025-01-0122113310.1186/s41239-024-00501-1Enhancing peer assessment with artificial intelligenceKeith J. Topping0Ed Gehringer1Hassan Khosravi2Srilekha Gudipati3Kaushik Jadhav4Surya Susarla5University of DundeeNorth Carolina State UniversityUniversity of QueenslandNorth Carolina State UniversityNorth Carolina State UniversityNorth Carolina State UniversityAbstract This paper surveys research and practice on enhancing peer assessment with artificial intelligence. Its objectives are to give the structure of the theoretical framework underpinning the study, synopsize a scoping review of the literature that illustrates this structure, and provide a case study which further illustrates this structure. The theoretical framework has six areas: (i) Assigning Peer Assessors, (ii) Enhancing Individual Reviews, (iii) Deriving Peer Grades/Feedback, (iv) Analyzing Student Feedback, (v) Facilitating Instructor Oversight and (vi) Peer Assessment Systems. The vast majority of the 79 papers in the review found that artificial intelligence improved peer assessment. However, the focus of many papers was on diversity in grades and feedback, fuzzy logic and the analysis of feedback with a view to equalizing its quality. Relatively few papers focused on automated assignment, automated assessment, calibration, teamwork effectiveness and automated feedback and these merit further research. This picture suggests AI is making inroads into peer assessment, but there is still a considerable way to go, particularly in the under-researched areas. The paper incorporates a case study of the RIPPLE peer-assessment tool, which harnesses student wisdom, insights from the learning sciences and AI to enable time-constrained educators to immerse their students in deep and personalized learning experiences that effectively prepare them to serve as assessors. Once trained, they use a comprehensive rubric to vet learning resources submitted by other students. They thereby create pools of high-quality learning resources which can be used to recommend personalized content to students. RIPPLE engages students in a trio of intertwined activities: creation, review and personalized practice, generating many resource types. AI-driven real-time feedback is given but students are counseled to assess whether it is accurate. Affordances and challenges for researchers and practitioners were identified.https://doi.org/10.1186/s41239-024-00501-1Peer assessmentArtificial intelligenceTheoryScoping reviewCase study |
| spellingShingle | Keith J. Topping Ed Gehringer Hassan Khosravi Srilekha Gudipati Kaushik Jadhav Surya Susarla Enhancing peer assessment with artificial intelligence International Journal of Educational Technology in Higher Education Peer assessment Artificial intelligence Theory Scoping review Case study |
| title | Enhancing peer assessment with artificial intelligence |
| title_full | Enhancing peer assessment with artificial intelligence |
| title_fullStr | Enhancing peer assessment with artificial intelligence |
| title_full_unstemmed | Enhancing peer assessment with artificial intelligence |
| title_short | Enhancing peer assessment with artificial intelligence |
| title_sort | enhancing peer assessment with artificial intelligence |
| topic | Peer assessment Artificial intelligence Theory Scoping review Case study |
| url | https://doi.org/10.1186/s41239-024-00501-1 |
| work_keys_str_mv | AT keithjtopping enhancingpeerassessmentwithartificialintelligence AT edgehringer enhancingpeerassessmentwithartificialintelligence AT hassankhosravi enhancingpeerassessmentwithartificialintelligence AT srilekhagudipati enhancingpeerassessmentwithartificialintelligence AT kaushikjadhav enhancingpeerassessmentwithartificialintelligence AT suryasusarla enhancingpeerassessmentwithartificialintelligence |