Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning

TL;DR

This paper develops embedding-based models using large language models to automatically detect socially shared regulation of learning behaviors in collaborative environments, enhancing real-time feedback and adaptive support.

Contribution

It introduces a novel approach combining LLM-generated summaries with multimodal features to improve detection of SSRL behaviors in collaborative learning settings.

Findings

Text-only embeddings excel at detecting group dynamics and enactment behaviors.

Contextual and multimodal features complement text embeddings for planning and reflection detection.

Embedding-based models show promise for scalable, real-time learning analytics.

Abstract

The field of learning analytics has made notable strides in automating the detection of complex learning processes in multimodal data. However, most advancements have focused on individualized problem-solving instead of collaborative, open-ended problem-solving, which may offer both affordances (richer data) and challenges (low cohesion) to behavioral prediction. Here, we extend predictive models to automatically detect socially shared regulation of learning (SSRL) behaviors in collaborative computational modeling environments using embedding-based approaches. We leverage large language models (LLMs) as summarization tools to generate task-aware representations of student dialogue aligned with system logs. These summaries, combined with text-only embeddings, context-enriched embeddings, and log-derived features, were used to train predictive models. Results show that text-only embeddings often achieve stronger performance in detecting SSRL behaviors related to enactment or group dynamics (e.g., off-task behavior or requesting assistance). In contrast, contextual and multimodal features provide complementary benefits for constructs such as planning and reflection. Overall, our findings highlight the promise of embedding-based models for extending learning analytics by enabling scalable detection of SSRL behaviors, ultimately supporting real-time feedback and adaptive scaffolding in collaborative learning environments that teachers value.