Social network analysis for startups / Maksim Tsvetovat and Alexander Kouznetsov.

CONTENIDO
1. Introduction 1
Analyzing Relationships to Understand People and Groups 2
Binary and Valued Relationships 2
Symmetric and Asymmetric Relationships 3
Multimode Relationships 3
From Relationships to Networks - More Than Meets the Eye 3
Social Networks vs. Link Analysis 4
The Power of Informal Networks 6
Terrorists and Revolutionaries: The Power of Social Networks 10
Social Networks in Prison 10
Informal Networks in Terrorist Cells 11
The Revolution Will Be Tweeted 14
2. Graph Theory - A Quick Introduction 19
What Is a Graph? 19
Adjacency Matrices 21
Edge-Lists and Adjacency Lists 22
7 Bridges of Konigsberg 23
Graph Traversals and Distances 25
Depth-First Traversal 27
Breadth-First Traversal 30
Paths and Walks 31
Dijkstra's Algorithm 33
Graph Distance 35
Graph Diameter 36
Why This Matters 36
6 Degrees of Separation is a Myth! 37
Small World Networks 37
3. Centrality, Power, and Bottlenecks 39
Sample Data: The Russians are Coming! 39
Get Oriented in Python and NetworkX 39
Read Nodes and Edges from LiveJournal 41
Snowball Sampling 43
Saving and Loading a Sample Dataset from a File 44
Centrality 45
Who Is More Important in this Network? 45
Find the "Celebrities" 45
Find the Gossipmongers 49
Find the Communication Bottlenecks and/or Community Bridges 51
Putting It Together 54
Who Is a "Gray Cardinal"? 55
Klout Score 57
Page Rank - How Google Measures Centrality 58
What Can't Centrality Metrics Tell Us? 60
4. Cliques, Clusters and Components 61
Components and Subgraphs 61
Analyzing Components with Python 62
Islands in the Net 62
Subgraphs - Ego Networks 65
Extracting and Visualizing Ego Networks with Python 65
Triads 67
Fraternity Study - Tie Stability and Triads 68
Triads and Terrorists 68
The "Forbidden Triad" and Structural Holes 72
Structural Holes and Boundary Spanning 73
Triads in Politics 74
Directed Triads 76
Analyzing Triads in Real Networks 77
Real Data 79
Cliques 79
Detecting Cliques 79
Hierarchical Clustering 81
The Algorithm 82
Clustering Cities 83
Preparing Data and Clustering 84
Block Models 86
Triads, Network Density, and Conflict 88
5. 2-Mode Networks 93
Does Campaign Finance Influence Elections? 93
Theory of 2-Mode Networks 96
Affiliation Networks 96
Attribute Networks 98
A Little Math 98
2-Mode Networks in Practice 100
PAC Networks 102
Candidate Networks 102
Expanding Multimode Networks 105
Exercise 107
6. Going Viral! Information Diffusion 109
Anatomy of a Viral Video 109
What Did Facebook Do Right? 110
How Do You Estimate Critical Mass? 111
Wikinomics of Critical Mass 112
Content is (Still) King 113
How Does Information Shape Networks (and Vice Versa)? 116
Birds of a Feather? 117
Homophily vs. Curiosity 117
Weak Ties 119
Dunbar Number and Weak Ties 119
A Simple Dynamic Model in Python 121
Influences in the Midst 125
Exercises for the Reader 127
Coevolution of Networks and Information 127
Exercises for the Reader 133
Why Model Networks? 134
7. Graph Data in the Real World 137
Medium Data: The Tradition 138
Big Data: The Future, Starting Today 138
"Small Data" - Flat File Representations 139
EdgeList Files 139
.net Format 140
GML, GraphML, and other XML Formats 141
Ancient Binary Format - ##h Files 142
"Medium Data": Database Representation 142
What are Cursors? 143
What are Transactions? 144
Names 144
Nodes as Data, Attributes as? 145
The Class 145
Functions and Decorators 146
The Adaptor 148
Working with 2-Mode Data 150
Exercises for the Reader 151
Social Networks and Big Data 151
NoSQL 152
Structural Realities 153
Computational Complexities 156
Big Data is Big 156
Big Data at Work 156
What Are We Distributing? 157
Hadoop, S3, and MapReduce 157
Hive 158
SQL is Still Our Friend 160
A. Data Collection 161
B. Installing Software 171