Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
For educational researchers and instructors, this work proposes a method to analyze student engagement without storing identifiable video, addressing privacy concerns, though results are preliminary and limitations are acknowledged.
The paper presents a privacy-preserving pipeline that uses OpenPose and Gaze-LLE to extract skeletal and gaze data from classroom videos, then employs QwQ-32B-Reasoning for zero-shot analysis of student attention, with results displayed via a web dashboard. Preliminary findings indicate LLMs show promise but struggle with spatial reasoning.
Understanding student engagement usually requires time-consuming manual observation or invasive recording that raises privacy concerns. We present a privacy-preserving pipeline that analyzes classroom videos to extract insights about student attention, without storing any identifiable footage. Our system runs on a single GPU, using OpenPose for skeletal extraction and Gaze-LLE for visual attention estimation. Original video frames are deleted immediately after pose extraction, thus only geometric coordinates (stored as JSON) are retained, ensuring compliance with FERPA. The extracted pose and gaze data is processed by QwQ-32B-Reasoning, which performs zero-shot analysis of student behavior across lecture segments. Instructors access results through a web dashboard featuring attention heatmaps and behavioral summaries. Our preliminary findings suggest that LLMs may show promise for multimodal behavior understanding, although they still struggle with spatial reasoning about classroom layouts. We discuss these limitations and outline directions for improving LLM spatial comprehension in educational analytics contexts.