Scaling Cognitive Science and Dynamics of Social Interaction in Naturalistic Settings

Explore cutting-edge research on scaling cognitive science to understand social interaction dynamics in natural settings through this conference talk. Delve into two early-stage projects leveraging high-dimensional data presented by Robert Hawkins from Princeton University at IPAM's Analyzing High-dimensional Traces of Intelligent Behavior Workshop. Discover how vest-mounted video cameras capture rich, multimodal data streams of preschoolers' free play, enabling analysis of peer interactions and social learning opportunities. Learn about the application of advanced speech recognition and natural language processing techniques to extract and analyze sentence frames from this complex data. Investigate the second project focusing on trajectories through topic space in everyday conversation, utilizing the extensive CANDOR corpus. Gain insights into how machine learning techniques uncover high-dimensional patterns in social dynamics, showcasing the potential of large-scale, multimodal datasets to advance our understanding of social intelligence.