LLMs as Educational Analysts: Transforming Multimodal Data Traces into Actionable Reading Assessment Reports

This paper develops a system using LLMs to transform multimodal data (eye-tracking, learning outcomes, assessment content) into actionable reading assessment reports for K-12 teachers. The system uses unsupervised clustering to identify reading behavior patterns and LLMs to synthesize insights into teacher-friendly reports, which are then evaluated by educators and LLM experts.

Reading assessments are essential for enhancing students' comprehension, yet many EdTech applications focus mainly on outcome-based metrics, providing limited insights into student behavior and cognition. This study investigates the use of multimodal data sources -- including eye-tracking data, learning outcomes, assessment content, and teaching standards -- to derive meaningful reading insights. We employ unsupervised learning techniques to identify distinct reading behavior patterns, and then

Study Type

Source

Framework Categories

Tool Types

Tags