John Templon, Data Reporter for Buzzfeed, decided to use Social Network Analysis to create an interactive map to showcase Donald Trump’s affiliations with various organizations. The interact chart went live on Buzzfeed a week before Trump took charge at the office.

 

 

 

 

 

 

 

 

 

 

 

 

 


The team at Buzzfeed spent weeks curating this data from public documents and mapping over 2,400 people and organizations connected to Trump. In the article published Buzzfeed team asked viewers to suggest people and organizations connected to Trump which they would have probably missed out in the chart. Network analysis is increasingly used by brands and publishers to identify relations and the value they hold.

Mathematician Leonard Euler among the first use network analysis said ““Logic is the foundation of the certainty of all the knowledge we acquire.” In his very first example, Euler uses network analysis for the city of königsberg (now Kaliningrad, Russia) to prove that no path crosses each of cities bridges once.

Social Network Analysis (SNA) centers around relations between individuals, society, and organizations. SNA has caught the fancy of computer scientists who are now using it to study internet traffic, web pages and information dissemination on social networks. Social networking sites like Facebook use core elements of SNA to identify and recommend potential friends based on friends-of-friends. Consumer brands are using SNA to identify influencers and craft content that could be more valuable for the audience. SNA represents every relation in a network in form of a graph represented by nodes (vertex) and links (edge). Edges can represent interaction, flows of information for goods or services, similarities/affiliations, or social relations.

Why Should You Use Social Network Analysis?

Effectiveness & mapping

Social Network Analysis is useful if you wish to understand the effectiveness of network both offline or online. Network Analysis also helps you to map the flow of information in a network.

Uncover trends & Pattern

SNA is valuable if you are looking to discover new trends or patterns. Valdis E. Krebs, a network scientist in his widely praised paper, shared how network analysis can be used to identify terrorist networks.

Find value & Test Hypothesis

SNA can be used to test a hypothesis in online behavior and to determine causes for dysfunctional communities and networks, and to promote social cohesion and growth in the online community.

Centrality

Network Analysis Graph

If you have to understand network analysis more, you have to learn about centrality. In network analysis indicators of centrality allows you to identify most critical nodes in a graph. Centrality allows you to identify the most influential person in the network, key infrastructure nodes in an urban network, etc.

Degree Centrality

Degree Centrality

Degree Centrality measures the counts of how many neighbors a node has. There are two versions of the measure: In-degree is the number of incoming links, or the number of predecessor nodes; Out-degree is the number of outgoing links, or the number of successor nodes. For instance, you can use degree centrality to measure how often do your connections share content which would count as an in-degree measure. It’s important to measure in-degree as it comprises in-link which are given by other nodes in a network, while the node itself determines out-links.

Betweenness Centrality

Betweenness Centrality

Betweenness centrality measures the extent to which a node lies on paths between other nodes. A node with higher betweenness have a greater influence on the network and removing them from the network can cause disruptions.

Closeness Centrality

Closeness Centrality

Closeness centrality in graph measures the average length of the shortest path from a node to other nodes in a network. For instance, if you measure the closeness centrality for a website and its links you will find that the outgoing links have higher closeness compared to the incoming links.

Eigenvector Centrality

Eigenvector Centrality

Eigenvector Centrality measures the influence of a node in a network. Relative scores are assigned to each node based on connections to high scoring nodes and low scoring nodes. Google Page Rank was a variation of eigenvector centrality.

“If we are connected to everyone else by six degrees and we can influence them up to three degrees, then one way to think about ourselves is that each of us can reach about halfway to everyone else on the planet.”

Nicholas A. Christakis, Author & American Sociologist

Brands are increasing use social network analysis to make sense of social & user data. Data mined from online reputation tools is being analyzed to understand which nodes (users) have more influence in a network. To efficiently perform SNA you need knowledge of Python, R, and other statistical tools. If you remove the complexity of understanding SNA, it might hold the answer to the question of reaching out to halfway to everyone else on the planet.