Intellectual network

As explained in Knowledge Graphs and LLMs in Action

An intellectual network is a graph representing relationships among people involved in shared scholarly or professional activity.

An intellectual network is a graph of people connected by TALKED_ABOUT, TALKED_WITH, WORKS_WITH, and STUDENT_OF relationships. It supports analysis of scholarly influence, referrals, communities, and connections. section 6.2

Graph analytics distinguishes several structural roles:

• Influencers recommend or otherwise direct attention toward other people’s work. section 6.2
• Influencees become popular targets of referrals. section 6.2
• Bridges connect researcher communities that would otherwise be weakly connected or disconnected; betweenness centrality highlights them. section 6.2

Tracing cyclotron research influence

A variable-length Cypher path can follow WORKS_ON, WORKS_FOR, TALKED_ABOUT, TALKED_WITH, WORKS_WITH, and STUDENT_OF relationships for up to two hops, then return the matched influence network.

Figure 6.4 The intellectual influence network comprises the relations TALKED_ABOUT, TALKED_WITH, WORKS_WITH, and STUDENT_OF. Node styling is based on their betweenness centrality score.

Inspect a connected intellectual network whose node styling uses betweenness centrality to expose bridge figures. section 6.2

How Knowledge Graphs and LLMs in Action covers it

How deep it goes

Explains relationship modeling, centrality measures, visualization, and a two-hop query, without detailing algorithm internals.

Examples

Uses scientist relationships, cyclotron research, and university-to-university physics connections as network-analysis examples.

What it assumes

Assumes a knowledge graph containing people and scholarly relationship types.

What you can do after

Apply it via Neo4j’s Graph Data Science library to identify influencers, influencees, bridges, and focused referral paths.

How it connects

Connects knowledge graphs with graph analytics, PageRank, eigenvector centrality, node degree, and betweenness centrality.

liveBookmanning.com

Read Knowledge Graphs and LLMs in Action on liveBook Get the book at manning.com

Related concepts

• relation extractioncontrasts with · Relation extraction is a natural-language-processing technique that identifies semantic relationships between entities expressed in text.
• entity resolutionaddressed by · Entity resolution is the process of determining which records or mentions refer to the same real-world entity despite differences in their representations.

This explainer was generated by Manning's knowledge graph from the text of Knowledge Graphs and LLMs in Action. The section links point to the parts of the book it draws on.