# social network analysis tutorial

**Definition – What does Social Network Analysis (SNA) mean?**

Social network analysis (SNA) is a process of quantitative and qualitative analysis of a social network. SNA measures and maps the flow of relationships and relationship changes between knowledge-possessing entities. Simple and complex entities include websites, computers, animals, humans, groups, organizations and nations.

The SNA structure is made up of node entities, such as humans, and ties, such as relationships. The advent of modern thought and computing facilitated a gradual evolution of the social networking concept in the form of highly complex, graph-based networks with many types of nodes and ties. These networks are the key to procedures and initiatives involving problem solving, administration and operations.

A graph is used to represent the social media networks, which are heterogeneous and multi relational. In social media networks, relationship between two entities are represented as links.

Characteristics of social network

The social networks are mostly dynamic and its graphical representation depends on the nodes and edges added or deleted over time.

**Here are some characteristics of social media networks:**

**1. Densification power law:**

In recent research, it is concluded that the networks become more dense over time with an average degree increase and so the number of edges grow linearly in the number of nodes.

**Densification follows the growth power law as:**

e(t) a n(t)a

Where,

e(t) and n(t) are the number of edges and number of nodes at times t.

In this law, value of ‘a’ lies between 1 and 2; where a = 1 denotes the constant average degree of graph, while a = 2 denotes that the graph is extremely dense.

**2. Shrinking diameter:**

As the network grows, the effective diameter goes on decreasing.

**3. Heavy tailed out-degree and in-degree distribution:**

The number of out-degrees for a node is a heavy-tailed distribution and follows the power law as:

1/na

where,

‘n’ is the rank of node in sequence of decreasing out-degree and OCAC2.

The ‘in-degrees’ follow a heavy-tailed distribution though it seems to be more skewed than the ‘out-degrees’ distribution.

## Stream Cluster Analysis

**Software network analysis software**

**Types of Software**

Network analysis software generally consists of either packages based on graphical user interfaces (GUIs), or packages built for scripting/programming languages.

**GUI Packages**

In general, the GUI packages are easier to learn, while scripting tools are more powerful and extensible. Widely used, often open-sourced and well-documented GUI packages include EgoWeb 2.0 (open source), NetMiner, UCINet, Pajek (freeware), GUESS, ORA, Cytoscape, Gephi, SocNetV (free software) and muxViz (open source).

Private GUI packages directed at business customers include: Arcade Analytics, Idiro SNA Plus, Keyhubs, KeyLines, KXEN, Keynetiq, Linkurious, OrgAnalytix, Orgnet and Polinode.

**Scripting/Programming Tools**

Commonly used and well-documented scripting tools used for network analysis include: NetMiner with Python scripting engine, the statnet suite of packages for the R statistical programming language, igraph, which has packages for R and Python, muxViz (based on R statistical programming language and GNU Octave) for the analysis and the visualization of multilayer networks,^{[8]} the NetworkX library for Python, and the SNAP package for large-scale network analysis in C++ and Python. Though difficult to learn, some of these open source packages are growing much faster in terms of functionality and features than privately maintained software, and extensive documentation and tutorials are available.^{[9]}

All of the tools above contain visualization capabilities.

**Social Network Analysis Example**

**Social network Generation**

The forest-fire model is used in social network generation. This model is based on the condition that new nodes are attached to the network by burning through the existing edges in an epidemic fashion.

This model uses two parameters, the forward burning probability ‘p’ and backward burning ratio ‘r’.

For example: Consider a new node v, which arrives at time ‘t’ and attached to graph ‘Gt’.

Constructing graph ‘Gt’.

# Big Data Analytics

**Step1:** Initially, graph ‘Gt’ selects a node ‘x’ in a random fashion as an ambassador node and then creates a link with it.

**Step2**: The ‘y’ links, which are incident to ‘x’ links, are selected. Assume ‘y’ as a random number which is supposed to be distributed with mean (1-p)-1. Further, select the in-links in such a way that their probability of ‘r’ times is lower than out-links. This generates the nodes x1,x2,….xy at the another end of the selected edges.

**Step3**: New node v, generates the out-links to x1,x2….xy. Apply step2 recursively to each x1,x2…xy. Visit the nodes only once so as to prevent the cycle formation.

Pingback:My Homepage

Pingback:ankle brachial index compartment syndrome