skills.rest
xjtulyc
xjtulycCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

social-network-analysis

Build and analyze social network graphs from edge lists or adjacency matrices.

33|6|Updated Mar 17, 2026
Search Tags:#graph visualization#networkx#centrality#community detection#social networks#gephi export
One-click install
npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill social-network-analysis-xjtulyc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: social-network-analysis
Source: https://github.com/xjtulyc/awesome-rosetta-skills/tree/main/skills/10-sociology/social-network-analysis
Command: npx skills add https://github.com/xjtulyc/awesome-rosetta-skills --skill social-network-analysis-xjtulyc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires networkx, pandas, numpy, matplotlib, python-louvain, scipy, requests.

What problem does it solve?

Social Network Analysis helps you understand how people, organizations, or content interact by transforming raw relationships into measurable network structure.

Core Features & Use Cases

  • Build networks from edge lists and adjacency matrices: Convert tabular relationship data into NetworkX graphs (including weighted edges and node attributes).
  • Compute key network metrics: Measure centrality (degree, betweenness, closeness, eigenvector, PageRank) and quantify small-world characteristics.
  • Discover structure and communities: Detect communities with Louvain and Girvan–Newman, analyze bipartite relationships via projection, and visualize results for reporting.

Quick Start

Build a social network graph from your edge list and ask the AI to compute centrality, detect communities, visualize the network with community-colored nodes, and export a Gephi-ready file.

Frequently Asked Questions about social-network-analysis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a social network graph from an edge list and compute centrality metrics?▼

You can build a social network graph from tabular edge lists or adjacency matrices using NetworkX, then compute centrality metrics like degree, betweenness, closeness, and eigenvector centrality to measure node importance.

What is the best way to detect communities in a social network using Python?▼

Detecting communities in a social network is done using the Louvain method via python-louvain or Girvan-Newman algorithm, partitioning nodes into modularity-based clusters to reveal underlying structural groupings.

Can I export NetworkX graphs to Gephi for advanced graph visualization?▼

Yes, NetworkX graphs can be exported to Gephi-compatible file formats, enabling advanced graph visualization and interactive exploration of network structures, node attributes, and community color mappings.

Does this social network analysis approach support bipartite projection and small-world evaluation?▼

Social network analysis supports bipartite projection for analyzing two-mode relationships and evaluates small-world characteristics by measuring network properties like clustering coefficients and shortest path lengths.

What Python dependencies are required for modularity-based community detection and network analysis?▼

Modularity-based community detection and network analysis require Python with NetworkX, pandas, numpy, scipy, matplotlib, and python-louvain for data handling, numerical computation, plotting, and Louvain community detection.

Related Skills

Explore More Education & Research Skills→
ptreezhptreezh
24

processing-network-data

Convert raw relationship data into node lists, edge lists, and adjacency matrices.

Community
Intermediate
wosnatwosnat

cypher-queries

Run Cypher queries against a Neo4j knowledge graph using prepared templates.

Community
Advanced
xjtulycxjtulyc
33

network-analysis-math

Analyzes network data by computing metrics, detecting communities with graph tools.

Community
Advanced
FrancisVargaFrancisVarga

Graph Algorithms

Execute PageRank, Louvain, BFS, DFS, and shortest path algorithms on in-memory property graphs.

Community
Advanced