GLITTER: An AI-assisted Platform for Material-Grounded Asynchronous Discussion in Flipped Learning

2025-04-20

AI Summary

In flipped-classroom pre-class asynchronous discussions, students commonly exhibit fragmented participation, weak material relevance, inadequate preparation, difficulties in cognitive navigation, insufficient reflection, and contribution anxiety. To address these challenges, this study proposes an AI-driven asynchronous discussion support platform featuring a novel concept-dimension matching mechanism for dynamic content organization. The platform integrates conceptual graph construction, NLP-based semantic alignment, and generative summarization to enable fine-grained anchoring and visualization of discussion threads to textbook concepts. It further introduces concept-fusion scaffolding and personalized metacognitive reflection reports to enhance knowledge integration and self-regulated learning. A user study (n=12) demonstrates that the platform significantly improves participation levels and viewpoint diversity; 87% of participants reported markedly enhanced pre-class preparedness. The system effectively overcomes key limitations of conventional forums—namely, poor coupling between discussion content and instructional materials, insufficient cognitive guidance, and lack of reflective support.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning
• Natural Language Processing: Discourse, Pragmatics & Argument Mining

Application Category

• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Flipped classrooms promote active learning by having students engage with materials independently before class, allowing in-class time for collaborative problem-solving. During this pre-class phase, asynchronous online discussions help students build knowledge and clarify concepts with peers. However, it remains difficult to engage with temporally dispersed peer contributions, connect discussions with static learning materials, and prepare for in-class sessions based on their self-learning outcome. Our formative study identified cognitive challenges students encounter, including navigation barriers, reflection gaps, and contribution difficulty and anxiety. We present GLITTER, an AI-assisted discussion platform for pre-class learning in flipped classrooms. GLITTER helps students identify posts with shared conceptual dimensions, scaffold knowledge integration through conceptual blending, and enhance metacognition via personalized reflection reports. A lab study within subjects (n = 12) demonstrates that GLITTER improves discussion engagement, sparks new ideas, supports reflection, and increases preparedness for in-class activities.

Problem

• Engage with temporally dispersed peer contributions
• Connect discussions with static learning materials
• Prepare for in-class sessions based on self-learning

Innovation

• AI-assisted platform for material-grounded discussions
• Conceptual blending for knowledge integration
• Personalized reflection reports for metacognition