Cognitive MRI of AI Conversations: Analyzing AI Interactions through Semantic Embedding Networks

Published on December 9, 2025

Authors:
Alex Towell (lex@metafunctor.com)
John Matta (jmatta@siue.edu)

Abstract

Through a single-user case study of 449 ChatGPT conversations, we introduce a cognitive MRI applying network analysis to reveal thought topology hidden in linear conversation logs. We construct semantic similarity networks with user-weighted embeddings to identify knowledge communities and bridge conversations that enable cross-domain flow. Our analysis reveals heterogeneous topology: theoretical domains exhibit hub-and-spoke structures while practical domains show tree-like hierarchies. We identify three distinct bridge types that facilitate knowledge integration across communities.

๐ŸŒ Read Online ๐Ÿ“„ Download PDF GitHub Paper Slides

Cite This Work

Show BibTeX
@article{towell2025,
  title     = {"Cognitive MRI of AI Conversations: Analyzing AI Interactions through Semantic Embedding Networks"},
  author    = {"Alex Towell, John Matta"},
  year      = {2025},
  url       = {"https://metafunctor.com/publications/cognitive-mri/"},
  abstract  = {"Through a single-user case study of 449 ChatGPT conversations, we introduce a cognitive MRI applying network analysis to reveal thought topology hidden in linear conversation logs. We construct semantic similarity networks with user-weighted embeddings to identify knowledge communities and bridge conversations that enable cross-domain flow. Our analysis reveals heterogeneous topology: theoretical domains exhibit hub-and-spoke structures while practical domains show tree-like hierarchies. We identify three distinct bridge types that facilitate knowledge integration across communities.\n"}
}
#complex networks #AI conversation #semantic embedding #knowledge graphs #ChatGPT #network analysis #community detection #cognitive science