New LLM framework ClickSight interprets student learning strategies from clickstream data

Researchers have developed ClickSight, a framework designed to interpret student clickstream data from digital learning environments. By leveraging a staged LLM-based pipeline, ClickSight analyzes student behavior to identify and assess adherence to predefined learning strategies. Evaluations across two learning environments and 365 students demonstrated that ClickSight can generate high-quality, evidence-grounded interpretations, with reasoning models showing more consistent performance than instruction-tuned models. The framework aims to provide a flexible approach for studying student behavior by connecting fine-grained clickstream data with theoretical learning strategies. AI

IMPACT This framework could enhance educational analytics by providing deeper insights into student learning processes.

RANK_REASON The cluster describes a research paper detailing a new framework for analyzing student data using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• alphaXiv
• arXiv
• CatalyzeX
• ClickSight
• Connected Papers
• DagsHub
• Gotit.pub
• Hugging Face
• Litmaps
• ScienceCast

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →