An Explainable Graph Enhanced Ensemble for Confusion Detection and Multiple Strategy Intervention in Massive Open Online Course Discussion Forums

Creative Commons License

Redjaibia A., Drissi S., Boussaha K., GÜLSEÇEN S., Lafifi Y.

Journal of Communications Software and Systems, vol.22, no.3, pp.518-529, 2026 (ESCI, Scopus)

  • Publication Type: Article / Article
  • Volume: 22 Issue: 3
  • Publication Date: 2026
  • Doi Number: 10.24138/jcomss-2026-0091
  • Journal Name: Journal of Communications Software and Systems
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, Applied Science & Technology Source, Directory of Open Access Journals
  • Page Numbers: pp.518-529
  • Keywords: Confusion Detection, Explainable Artificial Intelligence, Graph Neural Networks, Intervention Systems, MOOC Discussion Forums, SHAP
  • Open Archive Collection: AVESIS Open Access Collection
  • Istanbul University Affiliated: Yes

Abstract

Learner confusion in Massive Open Online Course (MOOC) forums is a critical precursor to dropout. Existing detection methods often treat posts in isolation, ignoring structural discussion dynamics. We present ConFusionGraph, an end-to-end framework integrating confusion detection, explainable analysis, and personalized intervention. The methodology models forum interactions as heterogeneous graphs with five relation types capturing thread structure, authorship, and temporal dynamics. We employ a stacked ensemble combining gradient boosting, transformer-based language models, and a heterogeneous graph neural network. To ensure transparency, dual local and global feature attribution analyses reveal that while explicit flags dominate, structural features—such as thread mean confusion and reply degree—are top contributors. Furthermore, attribution-based clustering identifies two primary mechanisms: active questioning and confusion contagion. Experiments on a large-scale dataset (nearly 30,000 posts across 11 courses) demonstrate an accuracy of 89.2% and an AUC of 0.923. Confusion chain analysis provides empirical evidence of propagation through threads and crossthread contagion. These findings drive a multi-strategy intervention system offering peer answer retrieval, thread summarization, and personalized clarification. This provides a robust, contextaware mechanism to mitigate learner dropout through timely support.