Knowledge Synthesis Graph: An LLM-Based Approach for Modeling Student Collaborative Discourse
Asynchronous, text-based discourse—such as students’ posts in discussion forums—is widely used to support collaborative learning. However, the distributed and evolving nature of such discourse often makes it difficult to see how ideas connect, develop, and build on one another over time. As a result, learners may struggle to recognize relationships among ideas—a process that is critical for idea advancement in productive collaborative discourse. To address this challenge, we explore how large language models (LLMs) can provide representational guidance by modeling student discourse as a Knowledge Synthesis Graph (KSG). The KSG identifies ideas from student discourse and visualizes their epistemic relationships, externalizing the current state of collaborative knowledge in a form that can support further inquiry and idea advancement. In this study, we present the design of the KSG and evaluate the LLM-based approach for constructing KSGs from authentic student discourse data. Through multi-round human-expert coding and prompt iteration, our results demonstrate the feasibility of using our approach to construct reliable KSGs across different models. This work provides a technical foundation for modeling collaborative discourse with LLMs and offers pedagogical implications for augmenting complex knowledge work in collaborative learning environments.
We propose a generic representational structure for the KSG consisting of two types of nodes—Micro-idea and Synthesis Node—and the Epistemic Relation between them. In this study, we use social annotation as a concrete example to illustrate construction of the KSG. The representational design is informed by prior work on discourse graphs, concept mapping, and scholarly knowledge representation.
Our approach is implemented as a three-stage pipeline, incrementally processing discourse into a KSG leveraging LLMs.
Read more in the Project Homepage and Preprint.