#487: Integrating AI and Interaction Analysis: A Mixed-Methods Approach to Tracing Object-Based Participation in CSCL

This study introduces and employs a novel mixed-methods design that integrates computer vision, optical character recognition (OCR), and qualitative video-based interaction analysis to examine multimodal participation in Computer-Supported Collaborative Learning (CSCL), with a focus on typing as a key form of object-based interaction. This approach integrates two computational tools: a neural network–based system for mapping typing activity in group interaction videos and a screen recording analysis system for extracting typed input. Analyzing a collaborative robotics programming session among middle school students, the findings identify who typed, when, and what was typed, as well as dynamic shifts in participation, tool access, and role negotiation. The study contributes to more inclusive, scalable and grounded analyses of CSCL processes by bridging Artificial Intelligence-enhanced automation with human insight, surfacing patterns that warrant deeper qualitative investigation.