Social Media Analytics

(SMA)
CSDC304

Subject In-charge

Ms. Annies Minu

Assistant Professor

Email:
1
 Social Media Analytics
Lecture
Module II:
Social Network Structure, Measures
& Visualization

Content:
✔ Basics of Social Network Structure - Nodes, Edges & Tie
✔ Describing the Networks Measures - Degree Distribution, Density,
Connectivity, Centralization, Tie Strength & Trust
✔ Network Visualization - Graph Layout, Visualizing Network
features, Scale Issues.
✔ Social Media Network Analytics - Common Network Terms,
Common Social Media Network Types, Types of Networks,
Common Network Terminologies, Network Analytics Tools.

Department of Computer Engineering Social Media Analytics –Ms. Annies 2

 Books
1. Seven Layers of Social Media Analytics_ Mining
Business Insights from Social Media Text, Actions,
Networks, Hyperlinks, Apps, Search Engine, and
Location Data, Gohar F. Khan, (ISBN-10:
1507823207).

1. Analyzing the Social Web 1st Edition by Jennifer

Golbeck

1. Charu Aggarwal (ed.), Social Network Data

Analytics, Springer, 2011

1. Social Media Analytics [2015], Techniques and

Insights for Extracting Business Value Out of Social
Media, Matthew Ganis, Avinash Kohirkar, IBM Press
Department of Computer Engineering Social Media Analytics –Ms. Annies 3
 Useful Links
✔
1. https://cse.iitkgp.ac.in/~pawang/courses/SC16.html

2. https://onlinecourses.nptel.ac.in/noc20_cs78/preview

3. https://nptel.ac.in/courses/106106146

1. https://7layersanalytics.com/

Department of Computer Engineering Social Media Analytics –Ms. Annies 4

❑ Teaching Scheme
✔ Theory : 3 hours/week
✔ No. of Credits :3

❑ Examination Scheme
✔ IAT1 & IAT2 : 20 marks each (Average of the two)
✔ End Semester Exam : 80 marks

❑ Assignments
✔ Assignment Test 1 or 2 (20 marks each)

❑ Quiz and Video Presentation

✔ Graded Quiz after each module

✔ Video Presentation (Individual/Group)
Department of Computer Engineering Social Media Analytics –Ms. Annies 5
Course Outcomes

Department of Computer Engineering Social Media Analytics –Ms. Annies 6

 Social Network Structure,
Measures & Visualization

Department of Computer Engineering Social Media Analytics –Ms. Annies 7

Social Network Structure, Measure
& Visualization :
❑Social networks are websites and apps that allow users and
organizations to connect, communicate, share information and
form relationships.

❑A social network is a social structure that exists between

actors—individuals or organizations

❑Social media metrics is the use of data to gauge the impact

of social media activity on a company's revenue

❑The Social Network graph helps you to visualize the

relationships between the selected entity and all entities
that the selected entity is linked to.

Department of Computer Engineering Social Media Analytics –Ms. Annies 8

Social Network Structure, Measures & Visualization

🡪 Basics of Social Network

Structure:
Nodes, Edges & Tie

Department of Computer Engineering Social Media Analytics –Ms. Annies 9

Social Network Structure, Measures & Visualization

A network or graph is a set of nodes and edges.

Department of Computer Engineering Social Media Analytics –Ms. Annies 10

Basics of Social Network Structure:
Nodes, Edges & Tie
● Social network structure refers to the patterns of
relationships and connections among a group of
people or organizations.
● How information, resources, and support flow within a
group, and how this flow impacts the behavior and
outcomes of individuals and organizations.
● Social network analysis is a research methodology that
uses mathematical and statistical techniques to
analyze and visualize social network data.
● Gain insights into the structure and dynamics of
social systems, and how these systems influence the
behavior and outcomes of individuals and
organizations within them.
● Social networks are composed of nodes and ties
Department of Computer Engineering Social Media Analytics –Ms. Annies 11
 Network Structure

Fig: A sample undirected network Fig: A sample directed graph

Department of Computer Engineering Social Media Analytics –Ms. Annies 12
Social Network Structure, Measures & Visualization

🡪 Describing the Networks

Measures:
Degree Distribution, Density,
Connectivity, Centralization,
Tie Strength & Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 13

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 14

Describing the Networks Measures:
❑ Node in Social Media Network
✔ A network or graph is a set of nodes and edges.

✔ A node refers to an individual, organization, or group that is

represented by a point in the network.

✔ A node is connected to other nodes by lines or edges, which

represent relationships or connections between the nodes.

✔ These connections can be based on various factors, such as

friendships, familial relationships, shared interests, or professional
connections.

Department of Computer Engineering Social Media Analytics –Ms. Annies 15

Social Network Structure, Measures & Visualization

✔Classic social network analysis studies a network’s

structure.
✔In a social network, a person is considered a node or
vertex, and a relationship between people is a link or
edge.
✔When all the people and relationships are identified,
there are many statistics that can provide insight into
the network.
✔Tie strength, which is the strength of the relationship
between two people, and trust are two relationship
features that have great impact on what happens in a
social network.

Department of Computer Engineering Social Media Analytics –Ms. Annies 16

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 17

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 18

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 19

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 20

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 21

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 22

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 23

Describing the Networks Measures:
❑ A number of measures can be used to describe the structure of
a network as a whole.

Degree Distribution
Density
Connectivity
Centralization
Tie Strength & Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 24

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 25

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 26

Describing the Networks Measures:

Degree Distribution

Department of Computer Engineering Social Media Analytics –Ms. Annies 27

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 28

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 29

Degree Distribution
Degree is used to describe individual nodes.
To get an idea of the degree for all the nodes in the network, we
can build the degree distribution.
This shows how many nodes have each possible degree.
To create a degree distribution, calculate the degree for
each node in the network.
Table3.3 shows the degrees for each node in the graph shown in
Figure 3.1.
The next step is to count how many nodes have each degree.
This is totaled for each degree, including those for which there are
no nodes with that count.
Table 3.4 shows the node count for each degree in this network.
The most common way to show a degree distribution is in a
bar graph.
The x-axis has the degrees in ascending order, and the Y-
axis indicates how many nodes have a given degree.
For the data in Table 3.4, we would make a bar graph as shown in
Figure3.5.
Department of Computer Engineering Social Media Analytics –Ms. Annies 30
Degree Distribution

Department of Computer Engineering Social Media Analytics –Ms. Annies 31

Department of Computer Engineering Social Media Analytics –Ms. Annies 32
Department of Computer Engineering Social Media Analytics –Ms. Annies 33
Describing the Networks Measures:

Density

Department of Computer Engineering Social Media Analytics –Ms. Annies 34

Density
❑Density the number of edges in the graph divided
by the number of possible edges is one of the most
common ways of describing a network.

✔Calculating Density

✔Density In Egocentric Networks

Department of Computer Engineering Social Media Analytics –Ms. Annies 35

Density
✔Calculating Density
A nodes connections say a lot about its role in the network.
This goes well beyond the degree of a single node or the degrees of
all nodes in the network to understand both individual nodes and
the network as a whole is by studying density.
Density describe show who much connected a network is.
More formally, it is a statistic comparing the number of edges that
exist in a network to the number of edges that could possibly exist.
Consider the following two networks, which both have the same
number of nodes.
Network (a) has very few edges while network(b)has numerous
edges among the same number of nodes.
Therefore, network(b) has higher density.

There is a formula to calculate density:

number of edges / number of possible edges

Department of Computer Engineering Social Media Analytics –Ms. Annies 36

Density
✔Calculating Density

Department of Computer Engineering Social Media Analytics –Ms. Annies 37

Density
✔Calculating Density

Department of Computer Engineering Social Media Analytics –Ms. Annies 38

Density
✔Calculating Density

Department of Computer Engineering Social Media Analytics –Ms. Annies 39

Density
✔Density In Egocentric Networks

• Computing the density of each nodes egocentric network gives us a

way to compare nodes.
• Some will have dense egocentric networks, which means a lot of
their friends know one another.
• Others will have sparse egocentric networks, and thus we know
their connections often do not know one another.
• The density of an egocentric network is sometimes referred to as
the local clustering coefficient
• To compute the density of an egocentric network, we use the
1.5-diameter network.
• We consider the node’s connections and all the connections
between those nodes.
• For this calculation, the ego-node will be excluded from its
egocentric network because the density of interest is that of the
connections between the node’s friends

Department of Computer Engineering Social Media Analytics –Ms. Annies 40

Density
❑ Example- consider egocentric network of node A( fig (a)) and
node B ( fig (b))

Department of Computer Engineering Social Media Analytics –Ms. Annies 41

Density In Egocentric Networks

Department of Computer Engineering Social Media Analytics –Ms. Annies 42

Density In Egocentric Networks
⮚Example:
🞆 Density of egocentric network of node A : 2/3=0.667
🞆 Density of egocentric network of node B: 5/6=0.883
🞆 Thus, B’s egocentric network (0.833) is more dense than
A’s (0.667).

Note: However, having a higher egocentric network

density does not necessarily mean a node is more
“popular” or important. A node with a high degree
(connections to many other nodes) will usually have a
lower density. As the number of nodes in an egocentric
network increases, the number of possible edges
increases at that rate squared. Thus, more popular
nodes tend to have lower densities.

Department of Computer Engineering Social Media Analytics –Ms. Annies 43

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 44

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 45

Describing the Networks Measures:

Department of Computer Engineering Social Media Analytics –Ms. Annies 46

Describing the Networks Measures:

Connectivity

Department of Computer Engineering Social Media Analytics –Ms. Annies 47

Connectivity
▪ Density measures the percentage of possible edges in a graph.
▪ Connectivity, also known as cohesion, measures how those
edges are distributed.
▪ Connectivity is a count of the minimum number of nodes that
would have to be removed before the graph becomes
disconnected; that is ,there is no longer a path from each node to
every other node.
▪ In Figure 3.4, the connectivity is 1 because removing node B, C,
or D would disconnect the graph. Since removing anyone of those
nodes disconnects the graph, the connectivity is 1.

Department of Computer Engineering Social Media Analytics –Ms. Annies 48

Connectivity

Department of Computer Engineering Social Media Analytics –Ms. Annies 49

Connectivity

Department of Computer Engineering Social Media Analytics –Ms. Annies 50

Connectivity (Cohesion)

Department of Computer Engineering Social Media Analytics –Ms. Annies 51

Connectivity

Answer: The connectivity is 2.

🞆 Removing any one node would not break the graph

into two parts, but there are several options for
removing two nodes that would.
🞆 For example, removing nodes E and F would
separate G from the rest of the graph.
🞆 Also, removing nodes B and D would separate A
from the rest of the graph.

Department of Computer Engineering Social Media Analytics –Ms. Annies 52

Connectivity

Department of Computer Engineering Social Media Analytics –Ms. Annies 53

Exercise

Department of Computer Engineering Social Media Analytics –Ms. Annies 54

Exercise

Department of Computer Engineering Social Media Analytics –Ms. Annies 55

Exercise

Department of Computer Engineering Social Media Analytics –Ms. Annies 56

Describing the Networks Measures:

Centralization

Department of Computer Engineering Social Media Analytics –Ms. Annies 57

Centralization
Centrality is an important way to understand the role
of a node in the network and to compare nodes.
Centralization uses the distribution of a centrality
measure to understand the network as a whole.
Any of the centrality measures presented above can be
used, but only one is used at a time when computing
centralization.
Centralization is computed by looking at the sum of the
differences in centrality between the most central node
and every other node in the network, and dividing this
by the maximum possible difference in centrality that
could exist in the graph (Freeman,1979).

There are different centrality measures for a graph

(e.g., betweenness, closeness, etc.)
Department of Computer Engineering Social Media Analytics –Ms. Annies 58
Centralization
Let C(n) be the centrality of node n, using whatever centrality
measure we choose.
Say n is the most central node.
We want to find the difference in centrality between n and every
other node in the network, and add those up.
If there are N nodes in the network, the formula for this is:

Then, we want to divide this by the sum of the maximum possible

differences between n and every other node. However, this
maximum possible centrality will change depending on which
centrality measure we are using.
Denote this by using the same formula with max in front:

Department of Computer Engineering Social Media Analytics –Ms. Annies 59

Centralization

Department of Computer Engineering Social Media Analytics –Ms. Annies 60

1. Degree Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 61

2. Closeness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 62

2. Closeness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 63

2. Closeness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 64

2. Closeness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 65

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 66

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 67

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 68

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 69

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 70

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 71

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 72

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 73

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 74

Betweenness Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 75

4. Eigenvector Centrality

Department of Computer Engineering Social Media Analytics –Ms. Annies 76

Exercise

Department of Computer Engineering Social Media Analytics –Ms. Annies 77

Describing the Networks Measures:

Tie Strength & Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 78

Tie Strength

Department of Computer Engineering Social Media Analytics –Ms. Annies 79

Tie Strength
❑ Measuring tie strength
Time can include the amount of time people spend with each other,
the duration of the relationship (i.e., how long they have known
each other), and how frequently they see one another.

Emotional intensity is indicated by the closeness of a relationship;

close friends or family members are likely to be strong ties, while
more casual friends and acquaintances would be weaker ties.

Intimacy or mutual confiding relates to people sharing secrets or

intimate personal details with one another.
The more of this information they exchange, the closer their
relationship is likely to be.

Reciprocal Services are favors that peopled of or one another.

They may be personal (e.g., pet sitting or picking up someone’s
dry cleaning),financial (e.g., loaning money),professional (e.g.,
putting people in contact with one another),or otherwise.
Department of Computer Engineering Social Media Analytics –Ms. Annies 80
Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 81

Trust
▪ A person trusts another if she is willing to take a risk based
on her expectation that the trusted persons actions will lead to
a positive outcome.

▪ Trust in social media provides evidence about with whom

we can trust to share information and from whom we can accept
information without additional verification.

Department of Computer Engineering Social Media Analytics –Ms. Annies 82

Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 83

Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 84

Categories of Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 85

Applications of Trust

Department of Computer Engineering Social Media Analytics –Ms. Annies 86

Social Network Structure, Measures & Visualization

🡪 Network Visualization:
Graph Layout, Visualizing
Network features, Scale Issues

https://kateto.net/2014/04/facebook-data-collection-and-photo-network-
visualization-with-gephi-and-r/#

Department of Computer Engineering Social Media Analytics –Ms. Annies 87

Network Visualization or (Network Graph)
▪ A network visualization is a good choice
to show connections, networks, and
points of intersection.
▪ It display a set of nodes represented
by symbols and links represented by
paths to show the relationship
between entities or items.
▪ The goal of information visualization is to
take advantage of humans natural
abilities to see patterns, anomalies,
relationships and features in visual data.
▪ It displays undirected and directed
graph structures.
▪ Visualization allows business users to
recognize relationships and patterns
between the data, and also gives it
greater meaning.
Fig: A node-link diagram
published by Twitter
Department of Computer Engineering Social Media Analytics –Ms. Annies 88
Network Visualization or (Network Graph)

Department of Computer Engineering Social Media Analytics –Ms. Annies 89

Network Visualization or (Network Graph)

❑ The researchers have presented some general

guidelines that make network visualizations easier
to work with (Dunne and Shneiderman, 2009):

1. Every node is visible.

2. For every node you can count its degree.
3. For every link you can follow it from source to
destination.
4. Clusters and outliers are identifiable.

Department of Computer Engineering Social Media Analytics –Ms. Annies 90

Network Visualization

Graph Layout

Department of Computer Engineering Social Media Analytics –Ms. Annies 91

Graph Layout
✔Random layout
✔Circular layout
✔Grid layout
✔Force-directed layout
✔Yifan Hu layout
✔Harel-Koren fast -
multiscale layout
✔Other layouts

Department of Computer Engineering Social Media Analytics –Ms. Annies 92

Graph Layout
✔Random Layout:

• When loading data into a

visualization tool, the nodes
are placed randomly. This is
called a random layout, and it
often does not provide much
insight into the structure of
the network.
• Figure 4.4 shows the same
network from Figure 4.3
presented in a random layout.
• We may be able to tell that
node a has a high degree in
this network, but the clusters
and other patters are not at
all clear from the random
layout.
Department of Computer Engineering Social Media Analytics –Ms. Annies 93
Graph Layout
✔Circular Layout:
• It place all the nodes in a circle
and then add edges between
them. Another way to do this is
to place nodes in a grid. Some
circular layouts place nodes
closer to one another when they
are more closely connected.
• In Fig. 4.5, the cluster of nodes
labeled a1 through a10 is clearer
because of the density of edges
in that section of the graph.
• The chain of nodes from b
through b4 is also present,
though the edges around the
circle are a bit harder to pick up
visually than in the Fig. 4.3
layout.
Department of Computer Engineering Social Media Analytics –Ms. Annies 94
Graph Layout
✔Grid layout
• Figure4.6 shows an
example of a grid
layout for the same
graph in Figures 4.3 –
4.5.
• Note that the degree
of node a is clearly
high, the cluster of
nodes a1 through a 10
is obvious, and the
chain of nodes b
through b4 is clear
across the top.

Department of Computer Engineering Social Media Analytics –Ms. Annies 95

Graph Layout
✔Force-directed Layout
• Most graphs are not laid out randomly or in one of these formats
with a pre determined structure. Instead, the layout is dynamic
and determined by the connections between the nodes.
Those nodes that are more closely connected are laid out close to
one another, and those that are distant are shown further a part.
• Figure 4.3 uses an algorithm that does this.
• Nodes and edges are treated as a physical system, and a
simulation of that system is applied to determine a final layout.
• For example, nodes may be treated as objects, and edges may
be
treated as springs that apply equal force.
• The nodes are randomly laid out, connected by springs for edges,
and then a simulation of how the springs would physically be
have determines the final position of nodes and edges.
• A cluster of nodes with many connections will be close together,
because pulling any node away pulls on many springs that want
to keep it close.
• Nodes with
Department little orEngineering
of Computer no connectionSocial
are not attracted
Media Analytics to one–Ms. Annies.
another 96
Graph Layout
✔ Yifan Hu Layout
• Many algorithms
lay out graphs in
this matter.
• Figure 4.3 uses
one called Yifan Hu
• Figure 4.7 uses a
variant called Force
Atlas.
• While there are
differences between
Figures 4.3 and 4.7,
the similarities in
clustering and
separate nodes are
clear.

Department of Computer Engineering Social Media Analytics –Ms. Annies 97

Graph Layout
✔Harel-Koren fast multiscale Layout
• The Harel-Koren fast multiscale
algorithm (Harel and Koren,
2000), available in NodeXL, is
designed to quickly lay out large,
complex graphs.

• It is based on force-directed
layout algorithms but uses
optimizations in the underlying
code to make the algorithm
computationally efficient.

• For large graphs with thousands

of nodes, generating a layout with
many force-directed algorithms
can take a very long time but with
Harel-koren often can be achieved
in a few seconds, making it an
ideal choice for large networks.
Department of Computer Engineering Social Media Analytics –Ms. Annies 98
Graph Layout
✔ Other Layouts
• Most graphs will be
presented using a force-
directed layout algorithm.

• However, there are some

more sophisticated layouts
designed to convey
additional information
through layout.

• Figure 4.9 shows a layout

available in the graphing
program NodeXL.

• Here, nodes are clustered,

grouped into boxes, and
then links are added within
and between boxes.
Department of Computer Engineering Social Media Analytics –Ms. Annies 99
Network Visualization

Visualizing Network features

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
0
Visualizing Network features
❑ The network features, like edge weights, node properties, labels, and
clusters, can also be visualized.

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
1
Visualizing Network features
✔Labels
Labels are some of the more difficult attributes to show in a network,
both on nodes and on edges. The example graphs in the previous section
all have node labels, but the graphs are small and the labels are short.
Figure 4.10 shows a net-work with only 92 nodes, which is still relatively
small.
The nodes represent YouTube videos, and the edges indicate that
they were tagged with at least one similar term.
The node labels are the YouTube identifiers for each video.
Even in this small graph, the image becomes very cluttered with all the
labels shown. Similar problems happen with edge labels. Whether shown
on top of the edge with straight alignment or angled along the edge, the
graph tends to become cluttered and difficult to read.
Some techniques can improve on this a bit, either by putting boxes
around the text, by only showing a few labels of interest, or by relying
on interactive interfaces that only show labels on demand. The latter
allow the user to move the mouse over a node or edge and see the label
or other data on demand. That facilitates exploration of the graph without
the clutter. Still, there are no solutions to totally eliminate this problem
when producing fixed visualization images, so often labels are left off.
10
Department of Computer Engineering Social Media Analytics –Ms. Annies
2
Visualizing Network features
✔ Size, Shape, and Color
Categorical or quantitative attributes are particularly easy to show by
adjustments in size, shape, or color Figures 4.3 - 4.8.
Figure 4.11 shows color encoding of node degree. Darker colors indicate
nodes with higher degrees, and not surprisingly, node a is the darkest.
Node color could also be used to indicate other attributes of a node.
For example, a person’s email indicate if each person is a friend, family
member, classmate, co-worker, and so forth.
Node size
anbeusedtoindicateotherattributes.Forexample,clusteringcoefficientisinteres
tinghere, since thereisatightclusterwhereall
thenodesareconnected,whileinthe rest ofthegraph,theclusteringcoefficient
isverylowforeachnode. Figure 4.12
showsagraphthatusescolorfordegreeandsizeforclustering coefficient.
Edgescanalsobetreatedwithcolororthicknesstoindicatetheirattributes.
Forexample, different types of relationships could each be coded in a
different color.
Edge weights are also commonly visualized.Thesecouldindicatethe
strengthofarelationship,thefrequencyofcommunication,orotherfactors.
Figure4.13 shows thesameexamplenetworkwithweightsaddedtotheedges.
10
Department of Computer Engineering Social Media Analytics –Ms. Annies
3
Visualizing Network features
✔ Size, Shape, and Color

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
4
Visualizing Network features
Size, shape, and color:

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
5
Visualizing Network features
Size, shape, and color:

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
6
Visualizing Network features
✔Larger Graph Properties
Larger graph properties can also be encoded in visualizations.
For example, clusters are sometimes apparent on their own (like
the group to the upper right in Figure 4.11), but visual properties
to indicate them will often clarify a visualization further.
Figure 4.13 shows a new graph that has two main clusters.
This graph is a network of YouTube videos, where nodes
represent videos and edges connected videos that share a
common tag.
All of these videos were tagged with the word “cubs”.
Even without the color coding, the two groups would be relatively
easy to see.
But using a community detection algorithm that groups nodes
into clusters, and then color coding by those clusters, makes it
even more apparent.
This is shown in Figure 4.14.

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
7
Visualizing Network features
✔Larger Graph Properties

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
8
Visualizing Network features
✔Larger Graph Properties

10
Department of Computer Engineering Social Media Analytics –Ms. Annies
9
Network Visualization

Scale Issues

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
0
 Scale Issues
The example networks shown so far have been
relatively small a few hundred nodes and a few
thousand edges.
Visualization is very useful for analyzing networks
of this size or smaller. When networks become
much larger, the quality of the visualization
diminishes. Figure 4.15 shows a network from a
peer-to-peer file sharing network. Nodes
represent hosts (computers participating in
the network), and edges represent
connections between them (usually one
computer downloading a file from another).
There are close to11,000nodesin thisnetwork with
roughly40,000 edges. Even with a very low
density (,0.001), there are still too many nodes
and edges to see much of anything.
Dependingonthestructureofthenetwork,itissometi
mespossibletogetuseful
visualizationswithuptoaround10,000nodes;
however,networksunder1,000
nodesaretypicallysafest

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
1
Scale Issues
✔Density
Density can also be a problem for
visualization, even if the number of
nodes is small. Figure 4.16 shows a
network of members of the U.S.
Senate. There are only 100 nodes but
over 4,100 edges. The edges indicate
that the senators have voted the same
way in at least one bill. The edges have
a weight, indicating the percentage of
bills on which the two senators have
voted in the same way. Figure 4.13 has
the edges filtered so that only those
with a weight of 40% or more are
visible. However, as this network
shows, there are no interesting pat-
terns visible with the threshold of 40%;
the network is simply too dense.

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
2
Scale Issues
✔Filtering for visual patterns
It is often difficult to see any patterns in very dense networks.
One way to compensate for this is to filter the networks when
possible.
For example, if we take the same network from Figure 4.13 and
filter the edges so that they only connect senators who have
voted the same way on at least two-thirds of the bills, the pat-
tern changes dramatically.
This is shown in Figure 4.17. In this figure, two clear clusters
emerge, representing the two major political parties.
Furthermore, five senators are pulled out from the major party
clusters along the center, indicating that they frequently vote
with members of both parties.

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
3
Scale Issues
✔Filtering for visual patterns

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
4
Scale Issues
✔Graph simplification
An active area of research in network visualization is graph
simplification.
Because large networks are very common when working with
social media, problems of scale are common.
Graph simplification techniques include grouping clusters of nodes
into a single node and representing the edges between clusters as
a single edge, representing structural patterns as representative
shapes, or showing only part of the graph at a time.
As an example, Figure 4.18 shows a tree-structured network
visualized with a tool called Space Tree (Plaisant et al., 2002).
The nodes and edges to the right of the first level are hidden but
are summarized with triangles.
The size, color, and angle of the triangles indicate the depth,
number of nodes, and width of the summarized structure.

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
5
Scale Issues
✔Graph simplification

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
6
Social Network Structure, Measures & Visualization

🡪 Social Media Network Analytics:

Common Network Terms
Common Social Media Network Types
Types of Networks
Common Network Terminologies
Network Analytics Tools

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
7
🡪 Social Media Network
❑Analytics
Social Media Network Analytics thus deals with constructing,
analyzing, and understanding social media networks.
❑ The purpose of network analysis is to:

✓Understand overall network structure:

for example, number of nodes, number of links, density,
clustering coefficient, and diameter.

✓ Find influential nodes and their rankings:

for example, degree, betweenness, and closeness centralities.

✓ Find important links and their rankings:

for example, weight, betweenness, and centrality.

✓ Find cohesive subgroups:

for example, pinpointing communities within a network.

✓Investigate multiplexity:
for example, analyzing comparisons between different link types,
such as friends vs. enemies.
11
Department of Computer Engineering Social Media Analytics –Ms. Annies
8
🡪 Social Media Network
Analytics

Common Network Terms

11
Department of Computer Engineering Social Media Analytics –Ms. Annies
9
Common Network Terms
❑ The following are some of the social media networks
common terms:

o NETWORK
o SOCIAL NETWORKS
o SOCIAL NETWORK SITE
o SOCIAL NETWORKING
o SOCIAL NETWORK ANALYSIS

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
0
Common Network Terms
o NETWORK
✔ A network is a group of nodes that are connected with links.
✔ Nodes (also known as vertices) can represent anything, including
individuals, organizations, countries, computers, websites, or any other
entities.
✔ Links (also known as ties, edges, or arcs) represent the relationship
among the nodes in a network.
✔ Networks can also exist among animals.

o 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.
✔ Links represent their relationships, such as friendship and trade relations.
✔ Social networks can exist both in the real and online worlds.
✔ A network among classmates is an example of real world social network
or a Twitter follow following network is an example of an online social
media network. In a Twitter follow-following network, nodes are the
Twitter users, and links among the nodes represents the follow-following
relationship (i.e., who is following whom) among the users.
12
Department of Computer Engineering Social Media Analytics –Ms. Annies
1
Common Network Terms
o 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.

o SOCIAL NETWORKING
The act of forming, expanding, and maintaining social relations is
called social networking.
Example, form, expand, and maintain online social ties with family,
friends, colleagues, and sometimes strangers.

o SOCIAL NETWORK ANALYSIS

Social network analysis is the science of studying and
understanding social networks (Hanneman and Riddle 2005) and
social networking. It is a well established field with roots in a variety
of disciplines including Graph Theory, Sociology, Information Science,
and Communication Science.
12
Department of Computer Engineering Social Media Analytics –Ms. Annies
2
🡪 Social Media Network
Analytics

Common Social Media Network Types

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
3
Common Social Media Network Types
❑ The following are some everyday types of social media networks
that we come across and that can be subject to network analytics.
o FRIENDSHIP NETWORKS
o FOLLOW-FOLLOWING NETWORKS
o FAN NETWORK
o GROUP NETWORK
o PROFESSIONAL NETWORKS
o CONTENT NETWORKS
o DATING NETWORKS
o COAUTHORSHIP NETWORKS
o COCOMMENTER NETWORKS
o COLIKE
o COOCCURRENCE NETWORK
o GEO COEXISTENCE NETWORK
o HYPERLINK NETWORKS

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
4
Common Social Media Network Types
❑The following are some everyday types of social media networks
that we come across and that can be subject to network
analytics:
FRIENDSHIP NETWORKS
✔Are Facebook, Google+, and Cyword. Friendship networks let people
maintain social ties and share content with people they closely associate
with, such as family and friends.
✔Nodes in these networks are people, and links are social relationships.
✔Example: friendship, family, and activities

FOLLOW-FOLLOWING NETWORKS
✔Users follow (or keep track of) other users of interested.
✔Twitter is a good example of follow-following network where users
follow influential people, brands, and organizations.
✔Nodes in these networks are, for example, people, brands, and
organizations, and links represents follow following relations
✔Example: who is following whom

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
5
Common Social Media Network Types
o FAN NETWORK
✔ A fan network is formed by social media fans or supporters of someone
or something, such as a product, service, person, brand, business, or
other entity.
✔ The network formed by the social media users subscribed to your
Facebook fan page is an example of a fan network.
✔ Nodes in these networks are fans, and links represent colikes,
cocomments, and coshares.

GROUP NETWORK
✔ Group networks are formed by people who share common interests and
agendas.
✔Most social media platforms allow the creation of groups where member
can post, comment, and manage in-group activities.
Examples of social media groups are Twitter professional groups, Yahoo
Groups, and Facebook groups.
✔Nodes in these networks are group members, and links can represent
✔cocommenting, coliking, and coshares.

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
6
Common Social Media Network Types

PROFESSIONAL NETWORKS
LinkedIn is a good example of professional networks where people manage their
professional identify by creating a profile that lists their achievements,
education, work history, and interests. Nodes in these networks are, for example,
people, brands, and organizations, and links are professional relations (such as
coworker, employee, or collaborator). An important feature of professional
networks is the endorsement feature, where people who know you can endorse
your skills and qualification.

CONTENT NETWORKS
Content networks are formed by the content posted by social media users. A
network among YouTube videos is an example of a content network. In such a
network, nodes are social media content (such as videos, tags, and photos) and
links can represent, for example, similarity (content belonging to the same
categories that can be linked together).

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
7
Common Social Media Network Types

DATING NETWORKS
Dating networks (such as match.com and Tender) are focused on matching and
arranging a dating partner based on personal information (such as age, gender,
and location) provided by a user. Nodes in these networks are people, and links
represent social relations (such as romantic relation).

COAUTHORSHIP NETWORKS
Coauthorship networks are two or more people working together to collaborate
on a project. Wikipedia (an online encyclopedia) is a good example of a social
media-based coauthorship network created by millions of authors from around
the world(Biuk-Aghai 2006). A more explicit example of the coauthorship
network is the ResearchGate platform: a social networking site for researchers to
share articles, ask and respond to questions, and find collaborators. In these
networks, nodes are, for example, researchers, and links represent the
coauthorship relationship.

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
8
Common Social Media Network Types

COCOMMENTER NETWORKS
Cocommenter networks are formed when two or more people comment on social
media content (e.g., a Facebook status update, blog post, or YouTube video). A
cocommenter network can, for example, be constructed from the comments
posted by users in response to a video posted over YouTube or a Facebook fan
page. In these networks, nodes represent users, and link represents the
cocommenting relationship.

COLIKE
In a similar way, colike networks are formed when two or more people like the
same social media content. Using NodeXL (a social network analysis tool), one
can construct a network based on colikes (two or more people liking a similar
content) over Facebook fan page. In such network, nodes will be Facebook
users/fans and links will be the colikes relationship.

12
Department of Computer Engineering Social Media Analytics –Ms. Annies
9
Common Social Media Network Types
COOCCURRENCE NETWORK
Cooccurrence networks are formed when two more entities (e.g., keywords,
people, ideas, and brands) cooccur over social media outlets. For example, one
can construct a cooccurrence network of brand names (or people) to investigate
how often certain brands (or people) cooccur over social media outlets. In such
networks, nodes will be the brand names and the links will represent the
cooccurrence relationships among the brands.
GEO COEXISTENCE NETWORK
Geo coexistence networks are formed when two more entities (e.g., people,
devices, and addresses) coexist in a geographic location. In such a network
nodes represents entities (e.g., people), and links among them represent
coexistence.
HYPERLINK NETWORKS
Hyperlink is a mechanism to move among electronic documents
(such as websites). Hyperlinks can be referred to as being either in-links (i.e.,
hyperlinks originating in other websites (Björneborn and Ingwersen 2004), thus
bringing traffic/users to your website) or out-links (i.e., links originating in your
website and going out (Bjorneborn 2001), thus sending traffic to other websites).
Hyperlink also forms networks. Typically, in these network nodes are website,
and links represent referral relationships (in the form of in-links or out-links).
13
Department of Computer Engineering Social Media Analytics –Ms. Annies
0
🡪 Social Media Network
Analytics

Types of Networks

13
Department of Computer Engineering Social Media Analytics –Ms. Annies
1
Types of Networks

From a technical point of view, 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
4) BASED ON WEIGHTS

13
Department of Computer Engineering Social Media Analytics –Ms. Annies
2
Types of Networks
1)BASED ON EXISTENCE
Based on the way the networks exist online or are constructed, they can be
classified as
1. Implicit Networks
Implicit networks do not exit by default (or are hidden) and need to be
intentionally constructed with the help of dedicated tools and techniques.
Examples of such networks include keyword cooccurrence networks, cocitation
networks, cocommenter networks, hyperlink networks, etc.
Constructing and studying implicit networks can provide valuable information
and insights.

2. Explicit Networks
Explicit social media networks exist by default; in other words, they are
explicitly designed for social media users to be part of. Most social media
networks are explicit in nature.
Examples of explicit social media networks include Facebook friendship network,
Twitter follow-following networks, LinkedIn professional networks, YouTube
subscribers’ network, and bloggers’ networks.

13
Department of Computer Engineering Social Media Analytics –Ms. Annies
3
Types of Networks

2) BASED ON DIRECTION OF LINKS

Based on the directions of links among the nodes, the networks can be
classified as 1) directed networks, and 2) undirected networks.
Directed Networks
A network with directed links among nodes is called a directed network
Usually, a link with an arrow is drawn to show the direction of the
relationship among the nodes.
For example, the Twitter following-following network is a directed
network where direction of the arrow shows who is
following whom.

Undirected Network
In undirected networks, the links among the nodes do not have any
direction. A Facebook friendship network is an example of undirected
network.

13
Department of Computer Engineering Social Media Analytics –Ms. Annies
4
Types of Networks
3) BASED ON MODE
Based on the composition of nodes, networks can be classified as 1) one-mode
network, 2) two-mode networks, and 3) multimode networks.
One-Mode Networks
A one-mode network is formed among a single set of nodes of the same nature.
A Facebook friendship network is an example of a one-mode network where nodes
(people) form network ties (friendships).

Two-Mode Networks
Two-mode networks (also known as bipartite networks) are networks with two
sets of nodes of different classes. In these networks, network ties exist only
between nodes belonging to different sets.
For example, consider the two-mode network given , where one set of nodes
(circles) could be social media users and other set of nodes (squares) could be
participation in a series of events. Users are linked to the events they attended.

Multimode Network
A multimode network is also possible where multiple heterogeneous nodes are
connected together. It can be considered as an amalgam of one and two-mode
networks.
13
Department of Computer Engineering Social Media Analytics –Ms. Annies
5
Types of Networks
4) BASED ON WEIGHTS
Networks can also be classified based the weight assigned to the links
among the nodes.
Mainly there are two types of weighted networks:

1)Weighted Networks
✔In weighted networks, the links among nodes bear certain weights to
indicate the strength of association among the nodes.
✔The link (relationship) between, for example, two Facebook friends
(nodes) will be thicker if they communicate more frequently.
✔Weighted networks can provide rich information, but are difficult to
construct.

2) Unweighted Networks
✔In unweighted networks, links among nodes does not bear weights.
✔The links only indicate the existence of a relationship and cannot provide
clues about the strength of relationship.
✔Unweighted networks are easy to construct, but may conceal useful
information.
13
Department of Computer Engineering Social Media Analytics –Ms. Annies
6
Types of Networks

13
Department of Computer Engineering Social Media Analytics –Ms. Annies
7
🡪 Social Media Network
Analytics

Common Network Terminologies

o NODE-LEVEL PROPERTIES
o NETWORK-LEVEL PROPERTIES

13
Department of Computer Engineering Social Media Analytics –Ms. Annies
8
Common Network Terminologies
❑Network terminologies or properties can be divided into two
categories:
1. NODE-LEVEL PROPERTIES
Node-level properties focus on one node and its position in the
network. Some important node properties include:

o Degree Centrality
Degree centrality of a node in a network measures the number
of links a node has to other node.
Example: In a Facebook network,it will measure the number
friendship ties a user has.
o Betweenness Centrality
Betweenness centrality is related to the centrality (or position)
of a node in a network. The nodes with high betweenness
centrality have the ability to control or facilitate collaboration or
flow of information due to their central position in the network
Example: In a Facebook friendship network, for the users who occupy the
central position are better positioned tocontrol the flow of social media content.
13
Department of Computer Engineering Social Media Analytics –Ms. Annies
9
Common Network Terminologies
o Eigenvector Centrality
Eigenvector centrality 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.

o Structural Holes
The idea of structural holes was first put forward by Burt, who
suggest that in a network exists when a certain node has an
advantage or disadvantage of its location in a network.
A node that is connected to users who are themselves not
directly connected has the opportunity to mediate between
them and profit from this mediation.

14
Department of Computer Engineering Social Media Analytics –Ms. Annies
0
Common Network Terminologies
2. NETWORK-LEVEL PROPERTIES
Network properties provide insight into the overall structure
and health of a network.
Important network-level properties include:
o Clustering Coefficient
The clustering coefficient of a network is the degree to which
nodes in a network tend to cluster or group together.

o Density
The density of a network deals with a number of links in a
network.
Density can be calculated as the number of links present in a
network divided by the number of all possible links between pairs
of nodes in a network (for an undirected network, the number of
all possible links can be calculated as n (n – 1)/2); where n is the
number of nodes in a network).
A fully connected network, in which each node is connected to
every other node, will have a density of 1.
14
Department of Computer Engineering Social Media Analytics –Ms. Annies
1
Common Network Terminologies
o Components
Components of a network are the isolated sub-networks that
connect within, but are disconnected between, sub-
networks.
In a connected component, all nodes are connected and reachable,
but there is no path between a node in the component and any
node not in the component. The main or largest component of a
network is the component with the largest number of nodes.

o Diameter
The diameter of a network is the largest of all the calculated
shortest path between any pair of nodes in a network and it
can provide an idea of how long it would take for some
information /ideas/message to pass through the network.

o Average Degree
The average degree centrality measures the average number of
links among nodes in a network.
14
Department of Computer Engineering Social Media Analytics –Ms. Annies
2
🡪 Social Media Network
Analytics

Network Analytics Tools

14
Department of Computer Engineering Social Media Analytics –Ms. Annies
3
 Network Analytics Tools
NodeXL: (an add-in for Microsoft Excel) is the free tool for
social network analysis and visualization.
It can help you construct and analyze Facebook networks (based on
colikes and cocomments), Twitter networks (followers, followings,
and tweets), and YouTube networks (user network and comments),
among others.

UCINET: is a social network analysis software application for

windows operating system.
It also includes Netdraw tool for network visualization.
It can be downloaded and used for free for 90 days:
https://sites.google.com/site/ucinetsoftware/home.

Pajek: (http://mrvar.fdv.uni-lj.si/pajek/ ) is a software

application for analyzing and visualizing large networks.
Pajek runs on Microsoft Windows operating systems and is free for
noncommercial use.

14
Department of Computer Engineering Social Media Analytics –Ms. Annies
4
 Network Analytics Tools
Netminer: (http://www.netminer.com/) is also a software
application for large social network analysis and visualization.
The application can used be for free for 28 days.

Flocker: Flocker (http://flocker.outliers.es/) is a Twitter real-

time retweets and mentions networks analytics tool.

Reach: Reach is an online platform to map hashtag networks

and identify the most influential accounts in the Twitter
conversation.
http://www.reachsocial. com/

Mentionmapp: This online tool is used to investigate Twitter

mentions networks.
(http://mentionmapp.com/)

14
Department of Computer Engineering Social Media Analytics –Ms. Annies
5
Social Media Analytics: An Overview

14
Department of Computer Engineering Social Media Analytics –Ms. Annies
6
 Thank you …

14
Department of Computer Engineering Social Media Analytics –Ms. Annies
7