Social Media Marketing

Analytics
Session 5
Dr. Mohit Malhan
 What is Social Media Network
Analytics?
• Social media network analytics deals with constructing, analyzing,
and understanding social media networks.

• NETWORKS ARE the building blocks of social media and can carry
useful business insights.
Purpose of Network Analysis
• Understand overall network
structure  Find important links and their
• number of nodes rankings weight
• number of links  betweenness and centrality.
• density  Find cohesive subgroups
• clustering coefficient, and  pinpointing communities
• diameter. within a network.
• Find influential nodes and their  Investigate multiplexity
rankings  analyzing comparisons
• Degree between different link types,
• Betweenness, and such as friends vs. enemies.
• closeness centralities.
Common Network Terms
• Network
• Social Networks
• Social Network Site
• Social Networking
• Social Network Analysis
Common Network Terms

• Network
• At a very basic level, a network is a group of nodes
that are connected with links.

 Nodes can represent:  Links represent the relationship

 Individuals among the nodes.
 Organizations  Friendship
 Countries  Trade
 Computers  Authorship
 websites, or  Hyperlinks
 any other entities.
Common Network Terms

• Social Networks
• A social network is a group of nodes and links
formed by social entities where nodes can represent
social entities such as people and organizations.

 Real World Social  Online Social Networks

Networks  A Twitter follow-
 A network among following network is
classmates is an an example of an
example of real world online social media
social network. network.
Common Network Terms

• Social Network Site

• A social network site is a special-purpose software
(or social media tool) designed to facilitate the
creation and maintenance of social relations.

 Examples:
 Facebook
 Google+, and
 LinkedIn
Common Network Terms

• Social Networking
• The act of forming, expanding, and
maintaining social relations is called
social networking.

 Using social network sites, users can, for example, form,

expand, and maintain online social ties with family, friends,
colleagues, and sometimes strangers.
Common Network Terms

• Social Network Analysis

• Social network analysis is the science of studying
and understanding social networks.

 Has root in variety of fields

 Graph Theory
 Sociology
 Information Science, and
 Communication Science.
Networks

• A network is a graph.
• Elements of the network have meanings
• Network problems can usually be represented in
terms of graph theory

Twitter example:
• Given a piece of information, a
network of individuals, and the
cost to propagate information
among any connected pair, find
the minimum cost to disseminate
the information to all individuals.
Social Networks: Examples
High school dating

High school friendship

https://www.youtube.com/watch?v=xT3EpF2EsbQ
Nodes and Edges

A network is a graph, or a collection of points connected by lines

• Points are referred to as nodes, actors, or vertices (plural of
vertex)
• Connections are referred to as edges or ties

Node
Edge
Nodes or Actors

• In a friendship social graph, nodes are people and any pair of

people connected denotes the friendship between them
• Depending on the context, these nodes are called nodes, or
actors
• In a web graph, “nodes” represent sites and the connection between
nodes indicates web-links between them
• In a social setting, these nodes are called actors

• The size of the graph is

Edges

• Edges connect nodes and are also known as ties or

relationships

• In a social setting, where nodes represent social entities such as

people, edges indicate internode relationships and are
therefore known as relationships or (social) ties

• Number is edges (size of the edge-set) is denoted as

Directed Edges and Directed Graphs

• Edges can have directions. A directed edge is

sometimes called an arc

• Edges are represented using their end-points

.
• In undirected graphs both representations are the
same
Neighborhood and Degree (In-degree, out-degree)

For any node 𝑣, in an undirected graph, the set of

nodes it is connected to via an edge is called its
neighborhood and is represented as 𝑁 𝑣

• In directed graphs we have incoming neighbors 𝑁𝑖𝑛 𝑣 (nodes

that connect to 𝑣) and outgoing neighbors 𝑁𝑜𝑢𝑡 𝑣 .

The number of edges connected to one node is the

degree of that node (the size of its neighborhood)
• Degree of a node 𝑖 is usually presented using notation 𝑑𝑖

In Directed graphs:
• In-degrees is the number of edges pointing towards a node

• Out-degree is the number of edges pointing away from a

node
Degree and Degree Distribution

• Theorem. The summation of degrees in an undirected graph is

twice the number of edges

• The number of nodes with odd degree is even

• In any directed graph, the summation of in-degrees is equal to
the summation of out-degrees,
Degree Distribution

When dealing with very large graphs, how nodes’

degrees are distributed is an important concept to
analyze and is called Degree Distribution

(Degree sequence)

is the number of
nodes with degree 𝑑
Degree Distribution Plot

The 𝑥-axis represents the degree and the 𝑦-axis

represents the fraction of nodes having that
degree

• On social networking sites

There exist many users with few
connections and there exist a
handful of users with very large
numbers of friends.
(Power-law degree distribution)

Facebook
Degree Distribution
Subgraph

• Graph 𝐺 can be represented as a pair

where 𝑉 is the node set and 𝐸 is the edge set

• is a subgraph of

5
6 4 5

3 1
1

3 2
2
 Graph Representation

• Adjacency Matrix
• Adjacency List
• Edge List
Graph Representation

• Graph representation is straightforward

and intuitive, but it cannot be
effectively manipulated using
mathematical and computational tools

• We are seeking representations that can

store these two sets in a way such that
• Does not lose information
• Can be manipulated easily by computers
• Can have mathematical methods applied easily
Adjacency Matrix (a.k.a. sociomatrix)

 1, if there is an edge between nodes 𝑣𝑖 and 𝑣𝑗

Aij = 
 0, otherwise

Diagonal Entries are self-links or loops

Social media networks have
very sparse Adjacency matrices
Adjacency List

• In an adjacency list for every node, we maintain

a list of all the nodes that it is connected to
• The list is usually sorted based on the node
order or other preferences
Edge List

• In this representation, each element is an edge

and is usually represented as 𝑢, 𝑣 , denoting
that node 𝑢 is connected to node 𝑣 via an edge
Common Social Media Network Types

 Friendship Networks  Co-authorship Networks

 Follow-Following Networks  Co-commenter Networks
 Fan Network  Co-like
 Group Network  Co-occurrence Network
 Professional Networks  Geo Co-existence Network
 Content Networks  Hyperlink Networks
 Dating Networks
Types of Networks
• The above-mentioned networks can be classified in a variety of
ways, including:
• 1) based on existence,
• 2) based on direction of links,
• 3) based on mode, and
• 4) based on weights.
Types of Networks

Figure 1. Types of social media networks

Types of Networks

• Network Types Based on Direction

1) Directed Networks 2) Undirected Network

A network with directed links In undirected networks, the links

among nodes is called a among the nodes do not have
directed network (Figure 1). any direction.
Types of Networks

• Network Types Based on Mode

1) One-Mode 2) Two-Mode Networks 3) Multimode

Networks Two-mode networks Network
A one-mode (also known as bipartite A multimode network
network is formed networks) are networks is also possible where
multiple
among a single set with two sets of nodes
heterogeneous nodes
of nodes of the of different classes.
are connected
same nature . together.
Types of Networks

• Network Types Based on Weights

1) Weighted Networks 2) Un-weighted Networks

In weighted networks, the In un-weighted networks,
links among nodes bear links among nodes does
certain weights to indicate not bear weights.
the strength of association
among the nodes.
Types of Networks

• Network Types Based on Existence

1) Implicit Networks 2) Explicit Networks

Implicit networks do not exit Explicit social media networks

by default (or are hidden) and exist by default; in other words,
need to be intentionally they are explicitly designed for
constructed with the help of social media users to be part of.
dedicated tools and
techniques.
Network types Examples

Type of Network Example

Directed Network Twitter follower-following network is a directed network where the direction of the arrow
shows who is following whom.
Undirected Network A Facebook friendship network is an example of an undirected network. As an example,
Facebook recently added the option to "follow" certain people's posts, similar to Twitter.
One-Mode Network A Facebook friendship network is an example of a one-mode network where nodes
(people) form network ties (friendships).
Two-Mode Network One set of nodes (circles) could be social media users and another set of nodes (squares)
could be linked to participation in a series of events. Essentially, a group of users are linked
to the events they attended.
Multi-Mode Network An amalgam of one and two-mode networks.

Weighted Network Facebook and LinkedIn use proprietary algorithms with weighted networks to condense a
user’s news feed with a preference towards users the member has interacted with
recently. Instagram also changed their algorithm, so images no longer appear
chronologically on their newsfeed, but based on the interests of the user.
Un-weighted Network Un-weighted networks are easy to construct but may conceal useful information – many
network maps are unweighted, by default.
Common Network Properties

• Node-Level Properties

 Degree Centrality https://www.youtube.com/watch?

v=NgUj8DEH5Tc
 Betweenness Centrality
 Eigenvector Centrality
Common Network Properties
Degree centrality of a node measures the number of links a node has to the
other nodes in a network.

In a Facebook network, for example, this

will measure the number of friends that a
member has.

In a Twitter network, it will equate to the

number of followers or following a user
has.

In a directed network, the degree can be

either in-degree (followers) or out-degree
In a Twitter network, in-degree (followers) is a more
(following).
important measure of a node’s influence than out-degree
(number of individuals a person follows).
Common Network Properties
Betweeness Centrality of a node is related to the centrality (or position) it
has in a network. Nodes with high betweeness centrality can control the flow
of information between connected nodes due to their central position in the
network.

For example: Your class-reps connect

teacher and students, thus control the
follow of information

(assuming that class reps is the only

way you can reach a teacher)
https://www.youtube.com/
watch?v=3X29Lfm6p2s
Common Network Properties

Figure : ITM institutional collaboration network (node size represents

betweenness centrality) (Source: Khan G. F., Jacob W. (2016)
Common Network Properties
Eigenvector Centrality of a node measures the importance of a
node based on its connections with other important nodes in a
network. It can provide an understanding of a node’s networking
ability relative to that of others.

E.g., Google search engine

use eigenvectors to rank
website based on
importance of in-links
Test your knowledge

• Consider the following sample network:

• How many nodes are in the network?

• How many edges are in the network?
• Is this graph directed or undirected?
• Which node(s) have the highest
degree? What is the degree? Which
node(s) have the lowest degree?
What is the degree?
• Which node has the highest
betweenness centrality?
Thanks