Artificial intelligence-based group decision making to improve knowledge transfer: the case of distance learning in higher education
Abstract
In this paper, we propose a method based on multicriteria classification and a dominancebased rough set approach (DRSA) to support teachers in decision making. The objective is to use teachers’ knowledge and preferences to identify ‘atrisk students’, i.e. students who are likely to drop out, and ‘leader students’, i.e. students who are likely to help their peers, in distance learning. The proposed method is composed of two phases: phase I builds collective decision rules from teachers’ preferences, and phase II classifies students into two decision classes: ‘atrisk students’ and ‘leader students’. This method was designed, tested, and validated in higher education, with teachers who have acquired rich experience in teaching in online-synchronous mode since the Covid-19 pandemic.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AI is found to accurately assess students' learning process and outcomes, and further determine teaching effect.
“AI is found to accurately assess students' learning process and outcomes, and further determine teaching effect (Novais et al., 2023;Saad and Tounkara, 2023;Wang et al., 2025;Zhu et al., 2023).”
From A systematic review of the early impact of artificial intelligence on higher education curriculum, instruction, and assessment (2025) · cites this paper as Saad and Tounkara, 2023
Saad and Tounkara (2023) used students' information, including class participation frequency and quality, absence rate, contribution to online group work, and utilization of learning resources, in distance learning, to establish a preference model for instructors that could quickly recognize students at risk of dropping out and leader students who could help their peers.
“Moreover, Saad and Tounkara (2023) used students' information, including class participation frequency and quality, absence rate, contribution to online group work, and utilization of learning resources, in distance learning, to establish a preference model for instructors that could quickly recognize students at risk of dropping out and leader students who could help their peers.”
From A systematic review of the early impact of artificial intelligence on higher education curriculum, instruction, and assessment (2025) · cites this paper as Saad and Tounkara (2023)
AI benefits assessments by generating personalized assignments, effectively assessing and predicting students' academic achievement and non-cognitive outcomes, identifying disadvantaged students, and assessing teaching effectiveness.
“Additionally, AI seems to benefit assessments by generating personalized assignments (Pereira et al., 2023), effectively assessing and predicting students' academic achievement (Wang et al., 2025) and non-cognitive outcomes (e.g., soft skills, Novais et al., 2023), identifying disadvantaged students (Saad and Tounkara, 2023), and assessing teaching effectiveness (Wang et al., 2025).”
From A systematic review of the early impact of artificial intelligence on higher education curriculum, instruction, and assessment (2025) · cites this paper as Saad and Tounkara, 2023
Cited by
Sorted by citations
Liang, J., Stephens, J. M., & Brown, G. T. L. (2025) · Frontiers in Education · doi:10.3389/feduc.2025.1522841 · Cited by 112 · see citing works
- Authors
- Saad, I., & Tounkara, T.
- Affiliations
- Amiens Business School &MIS Laboratory, Université de Picardie Jules Verne, Amiens, France
- Université Paris-Saclay, Univ Evry, IMT-BS, LITEM, Evry, France
- Venue
- Journal of Decision Systems
- Publisher
- Informa UK Limited
- Published
- 2023-03-19
- Pages
- 1-16
- ISSN
- 1246-0125
- 2116-7052
- Cited by
- 7
- References
- 0
- Language
- en
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
