Applying complex network analysis to ChatGPT conversation archives to reveal knowledge organization, community structure, and temporal evolution patterns.
Authors: Alexander Towell and John Matta, Southern Illinois University Edwardsville
This is the umbrella for a research program that transforms sequential AI conversation logs into semantic similarity networks, revealing latent cognitive structure in AI-assisted knowledge exploration. The program analyzes 1,908 ChatGPT conversations spanning December 2022 to April 2025. This repository is a landing page: it indexes the individual paper repositories and points to the shared data and pipeline.
Each paper is its own independent git repository under papers/ (not tracked by this
umbrella). Clone them individually.
| Paper | Venue / status | Path | Repository |
|---|---|---|---|
| Cognitive MRI of AI Conversations (semantic embedding networks) | Complex Networks 2025, Springer (published) | papers/knowledge-networks/ |
cmri-knowledge-networks |
| Temporal Evolution of Cognitive Knowledge Networks | PLOS Complex Systems (rejected 2026-04-27, seeking venue) | papers/temporal-networks/ |
cmri-temporal-networks |
| From Episodes to Abstractions: Latent Hierarchical Memory | ISCS 2026 | papers/hierarchical-memory/ |
cmri-hierarchical-memory |
| Embedding Dynamics | in progress | papers/embedding-dynamics/ |
cmri-embedding-dynamics |
| Semantic Dynamics | in progress | papers/semantic-dynamics/ |
cmri-semantic-dynamics |
| Operational Memex | early draft | papers/operational-memex/ |
cmri-operational-memex |
The published conference paper and the shared analysis pipeline (code/ and data/) live
in the knowledge-networks repository; the temporal-evolution journal extension is
temporal-networks.
papers/: the independent paper repositories (gitignored here; clone eachcmri-*repo into place, or work with them separately).chatgpt-conversation-corpus/: the sanitized, publishable conversation dataset, its own git repository (gitignored here). Derived fromdev/; pre-release, sanitization in progress.dev/: shared working corpus (gitignored; the raw conversation JSON the pipelines read).future-ideas/: early-stage directions not yet promoted to their own repos.docs/: program-level design and planning documents.
- Conversation corpus (dataset): chatgpt-conversation-corpus, co-located in this cluster at
chatgpt-conversation-corpus/. The sanitized, publishable version of the corpus (pre-release; sanitization in progress). - Analysis pipeline of record: chatgpt-complex-net (DOI: 10.5281/zenodo.15314235)
Child code reads the raw corpus from $CMRI_CORPUS_DIR, which defaults to this repo's dev/.
Cite the specific paper you use (each paper repository has its own CITATION.cff). To cite
the program as a whole, use the compendium DOI:
10.5281/zenodo.18778376. See
CITATION.cff for machine-readable metadata.