Research · Visualization1 Teaser PromptsNotebookLM + ChatGPT

How to Build a Literature Network Map with NotebookLM and ChatGPT

Extract author relationships and citation connections from your uploaded papers in NotebookLM, then have ChatGPT write the code that turns those relationships into a visual network graph — no data science background required.

TL;DR

Upload papers → prompt NotebookLM to extract author-citation pairs → paste structured output into ChatGPT → get networkx or D3.js visualization code → run and read the graph.

This workflow has been tested with literature sets from sociology, computer science, public health, and education research. The prompt templates below handle the most common edge cases. Written by a team of AI superusers who teach visualization workflows to graduate researchers. Updated March 2026.

What is a literature network map and why does it matter?

A literature network map is a graph where each node represents an author or paper, and each edge (connecting line) represents a citation relationship or shared reference. The map reveals things that are invisible in a reading list: which scholars are the hubs of a field, which research clusters cite only each other, and which papers bridge otherwise disconnected groups.

For researchers writing literature reviews, grant proposals, or dissertation chapters, a network map answers the question: "Who are the 5 people I absolutely must cite, and which intellectual communities am I implicitly positioning myself within?" That question is hard to answer by reading papers one at a time. It takes about 60 seconds to read in a good network graph.

The challenge is data extraction. Building the edge list — the table of "Paper A cites Paper B" relationships — from a collection of PDFs is tedious by hand. NotebookLM automates this with the right prompts, and ChatGPT writes the visualization code so you never need to learn Python or JavaScript.

What output does this workflow produce?

The end result is a rendered network graph you can export as PNG, SVG, or an interactive HTML file. Nodes are sized by centrality (how many connections they have). Clusters are color-coded by research group or sub-topic. You can click nodes in the interactive version to see paper titles. This is a publication-ready figure suitable for a dissertation chapter, conference poster, or grant background section.

HUB A BRIDGE HUB B Cluster A Bridge scholar Cluster B Isolated
Example network graph — hub nodes sized by citation count · dashed edge = cross-cluster bridge

The 5-step workflow

NLM

Step 1 — Upload papers and generate a source map

Upload 20–50 papers. Use NotebookLM's Mind Map feature first to get a visual sense of which concepts appear across multiple sources — this helps you decide which relationship type to extract (co-authorship, shared citation, or shared concept).

Name files with author last name and year: Noble-2018.pdf. NotebookLM uses filenames as source labels, which appear in your exported edge list.
NLM

Step 2 — Extract author and citation relationships

Use the extraction prompt below. Ask NotebookLM to list, for each paper, which other papers in the notebook it cites. The output is your raw edge list — the data that defines the network graph.

NLM

Step 3 — Format output as structured edge pairs

Ask NotebookLM to reformat the relationship list as edge pairs: "Source → Target" or CSV format. This structured output pastes cleanly into ChatGPT's code generation step without manual cleanup.

GPT

Step 4 — Generate visualization code in ChatGPT

Paste your edge list into ChatGPT with the code generation prompt. Specify: Python (networkx) for a static publication figure, or D3.js for an interactive web graph. ChatGPT writes the complete runnable script.

Upload the edge list as a .txt or .csv file in ChatGPT for cleaner parsing. Ask it to include node sizing by degree (connection count) and color coding by cluster.
RUN

Step 5 — Run the code and read the graph

Execute in Google Colab (free) or locally. Look for: hub nodes (high degree), isolated nodes (potential gaps in your literature), and bridge nodes (scholars connecting distinct clusters — often the most interesting for your own positioning).

What each tool contributes

TaskToolWhy this assignment
Extracting which papers cite whichNotebookLMRAG grounding — only cites what's actually in your uploaded documents
Formatting edge pairs for exportNotebookLMStructured output prompts work well in NLM's chat interface
Writing visualization codeChatGPTCanvas + code interpreter — iterates on code with live output preview
Debugging and styling the graphChatGPTCode interpreter runs the script and shows errors inline
Interpreting what the graph meansEitherClaude for analytical interpretation; ChatGPT for visual annotation

Teaser Prompts

1 prompt

Copy any prompt. Replace bracketed placeholders with your field details.

"For each source in this notebook, identify which other sources in this notebook it cites or directly references. Format the output as a list: [Citing Paper (Author, Year)] → [Cited Paper (Author, Year)]. Include only citations where both papers are present in this notebook. If a paper cites none of the other uploaded papers, note it as 'isolated.'" — Run in NotebookLM to extract your raw edge list.
Unlock All Prompts

Get the complete prompt library for this category.

Every prompt in this guide plus all prompts across the full category — advanced workflows, specialized use cases, and production-grade templates.

Category Bundle — one-time access

Unlock Category Prompts — $19.99

ONE-TIME · 30-DAY GUARANTEE · INSTANT ACCESS

Practical notes and known limitations

NotebookLM extracts citation relationships from what appears in your uploaded PDFs. If a paper's references section is poorly formatted or scanned as an image, extraction quality drops. For best results, upload text-layer PDFs from sources like Google Scholar, JSTOR, or Semantic Scholar rather than scanned documents.

For fields with very dense citation networks (100+ papers with 50+ references each), start with a subset: the 20 most-cited papers in your collection. Build the core graph first, then expand. A graph with 20 well-connected nodes is more readable and analytically useful than a hairball of 200.

ChatGPT's code interpreter can run your networkx code directly in the chat. You don't need to set up a local Python environment — just upload your CSV and ask it to execute. The rendered PNG will appear inline in the chat.

Frequently asked questions

What does a literature network map show?
A literature network map visualizes how authors, papers, and research groups are connected through shared citations and co-authorship. Nodes represent authors or papers; edges represent citation relationships. Hub nodes indicate influential scholars; isolated clusters indicate distinct intellectual traditions.
Can NotebookLM extract citation relationships automatically?
NotebookLM extracts information from whatever is in your uploaded documents. If your PDFs include references sections, NotebookLM can surface shared citations. For systematic extraction, use the structured prompts above to ask for author-to-author relationship lists formatted as edge pairs.
What visualization library does ChatGPT generate best for literature networks?
For static publication-ready graphs, Python's networkx with matplotlib works well. For interactive web-based graphs where you can click nodes, D3.js or Pyvis are better options. Specify your use case in the ChatGPT prompt — the templates above include options for both.
How do I run the Python code if I don't have Python installed?
Use Google Colab (colab.research.google.com) — it's free, requires no setup, and runs Python in your browser. Alternatively, use ChatGPT's code interpreter (Plus plan), which can run the networkx script directly in the chat window and display the rendered graph inline.
Related Guides
Research Paper Workflow Literature Review Grounded RAG Structured Distillation Hypothesis Generation PhD Literature Review
← Back to All Guides