EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

NeSy-Drop: Interpretable Dropout Prediction and Personalized Intervention via Neuro-Symbolic Graph Learning in MOOCs

Abdennour Redjaibia, Samia Drissi, Karima Boussaha, Yacine Lafifi, Sevinç Gülseçen

Electronics · 21.05.2026 · 15 (10) · 2212

DOI: 10.3390/electronics15102212 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 21.05.2026. Verfasst von Abdennour Redjaibia und 4 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dropout prediction in Massive Open Online Courses (MOOCs) has been extensively studied, yet existing systems share three fundamental limitations: Accurate models are black boxes, post-hoc explanations approximate rather than faithfully represent model decisions, and predictions are rarely translated into concrete instructor actions. This paper presents NeSy-Drop, a neuro-symbolic framework that simultaneously addresses prediction, explanation, and personalized intervention routing for MOOC dropout. NeSy-Drop constructs a heterogeneous graph per course cohort encoding student–resource–assessment interactions, processed through a heterogeneous graph transformer encoder, five behavioral atom predictor MLPs, and a differentiable symbolic rule layer producing guaranteed faithful ante-hoc explanations. A three-level explainability stack provides symbolic rule chains, SHAP embedding attribution, LIME raw-feature importance, and gradient-based counterfactual prescriptions. Each at-risk student is routed to one of five concrete interventions at one of three severity levels. Evaluated on OULAD covering 32,593 students across 22 cohorts, NeSy-Drop achieves AUC of 0.961 and macro F1 of 0.8983, within 2.2% AUC of the best non-interpretable baseline under a fair evaluation protocol, while being the only system that simultaneously predicts, explains, and prescribes actions at the individual student level.

Zitieren

APA

Redjaibia, A., Drissi, S., Boussaha, K., Lafifi, Y., & Gülseçen, S. (2026). NeSy-Drop: Interpretable Dropout Prediction and Personalized Intervention via Neuro-Symbolic Graph Learning in MOOCs. Electronics, 15(10), 2212. https://doi.org/10.3390/electronics15102212

Vancouver

Redjaibia A, Drissi S, Boussaha K, Lafifi Y, Gülseçen S. NeSy-Drop: Interpretable Dropout Prediction and Personalized Intervention via Neuro-Symbolic Graph Learning in MOOCs. Electronics. 2026;15(10):2212. doi:10.3390/electronics15102212

BibTeX
@article{Redjaibia2026,
  author = {Redjaibia, Abdennour and Drissi, Samia and Boussaha, Karima and Lafifi, Yacine and Gülseçen, Sevinç},
  title = {NeSy-Drop: Interpretable Dropout Prediction and Personalized Intervention via Neuro-Symbolic Graph Learning in MOOCs},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {10},
  pages = {2212},
  doi = {10.3390/electronics15102212}
}
Kostenlos starten →