Social Network Analytics – Session 1

COURSE EVALUATION COMPONENTS (CECs)

Project Presentation & Report (Max. 3 members in a group)
• Mid Term Review, Session 11 – 5%
• End Term Review & Report, Session 20 – 5% & 10%
Quiz (Each quiz will have 10 questions of 1 marks each) 20%
• Quiz 1 in Session 6 (10 marks) (Best of two will be taken)
• Quiz 2 in Session 12 (10 marks)
• Quiz 3 in Session 18 (10 marks)
In-class Assessment (Group activity) 10%

Mid Term exam 20 %

End Term exam 30%

17-10-2024 Presented by Dr. Purva Dureja 1

Social Network Analytics – Session 1

Social Network Analytics - Introduction

17-10-2024 Presented by Dr. Purva Grover 2

Social Network Analytics – Session 1

What is Social Network Analysis?

17-10-2024 Presented by Dr. Purva Grover 3

Social Network Analytics – Session 1

What is Social Network Analysis?

17-10-2024 Presented by Dr. Purva Grover 4

Social Network Analytics – Session 1

What is Social Network Analysis?

Network:
An abstract representation of relations
among entities

17-10-2024 Presented by Dr. Purva Grover 5

Social Network Analytics – Session 1

What is Social Network Analysis?

Network:
An abstract representation of relations
among entities

Social Network:
A simplified representation of the social
structure characterized by actors and ties

17-10-2024 Presented by Dr. Purva Grover 6

Social Network Analytics – Session 1

What is Social Network Analysis?

Network:
An abstract representation of relations
among entities

Social Network:
A simplified representation of the social
structure characterized by actors and ties

Social Network Analysis:

The application of networks and graph theory
to analyze the relations present in a society &
for us specifically how business is getting
influenced because of these interactions

17-10-2024 Presented by Dr. Purva Grover 7

Social Network Analytics – Session 1

Basics
❑ Relationship between two or more entities in the data
❑ Nodes: Represent Entities, i.e., city, person & many more
❑ Edge: Represent Relationship, i.e., can be directed or
undirected
❑ Directed Relationship: One way, i.e., “A person knows
another person”
❑ Undirected Relationship: Both ways, i.e., “Symmetric
Relationship”

17-10-2024 Presented by Dr. Purva Grover 8

Social Network Analytics – Session 1

Types of Graphs

Undirected Graph Directed Graph

17-10-2024 Presented by Dr. Purva Grover 9

Social Network Analytics – Session 1

Below graph is directed graph or undirected graph?

17-10-2024 Presented by Dr. Purva Grover 10

Social Network Analytics – Session 1

Below graph is directed graph or undirected graph?

17-10-2024 Presented by Dr. Purva Grover 11

Social Network Analytics – Session 1

Weights, Self loops, Parallel edges

Depending on the nature of application:
❑ Both the nodes and/or the linked are associated with one or more
attributes/features like weights, timestamps, textual features, etc.
❑ An edge in a graph may have same node as end nodes. Such edges of
a graph are called self loops (or, simply, loops).
❑ A graph may have more than one edge joining a pair of nodes. Such
edges are called parallel edges.

17-10-2024 Presented by Dr. Purva Grover 12

Social Network Analytics – Session 1

A Weighted Graph
❑ A graph having weights associated with
its edges are called a weighted graph.
❑ A weighted graph can be directed as well
as undirected.

17-10-2024 Presented by Dr. Purva Grover 13

Social Network Analytics – Session 1

A graph with loops and parallel edges

17-10-2024 Presented by Dr. Purva Grover 14

Social Network Analytics – Session 1

Business Applications
❑ Transmission of messages across the networks
❑ Recommender system
❑ Identifying influencers in the networks
❑ Page Ranking Algorithms
❑ Shortest Path Problem
❑ Small World Network

17-10-2024 Presented by Dr. Purva Grover 15

Social Network Analytics – Session 1

Recommender system - Netflix

Which movie will “X” watch
next?
Orange users had just seen “The Dark
Knight”.
Green users had just seen “Avengers:
Endgame”
Blue users had just seen “The Irishman”

17-10-2024 Presented by Dr. Purva Grover 16

Social Network Analytics – Session 1

Recommender system – Facebook, LinkedIn

Who will be X’s next

B C friend?
A A or B or C?

17-10-2024 Presented by Dr. Purva Grover 17

Social Network Analytics – Session 1

Usage of Graph in Marketing Analytics

❑ Identifying most influential people in Social Networks
❑ Routing message through most influential people

A sample of Twitter follower-followee network

(image source: http://allthingsgraphed.com/2014/11/02/twitter-friends-network/)

17-10-2024 Presented by Dr. Purva Grover 18

Social Network Analytics – Session 1

Usage of Graph in Banking Transactions

❑ Finding unusual patterns
❑ Helps in mitigating fraudulent transactions

17-10-2024 Presented by Dr. Purva Grover 19

Social Network Analytics – Session 1

Usage of Graph in Supply Chain

❑ Identifying optimum routes for deliveries & transporting raw
material
❑ Identifying locations for warehouses and delivery centers

17-10-2024 Presented by Dr. Purva Grover 20

Social Network Analytics – Session 1

Airlines Network
❑ Vertices - Airports
❑ Attributes – Footfall, Terminals, Staff, Population
❑ Edges – Airplanes Routes
❑ Attributes – Frequency, Plane Type, Fuel Usage, Distance covered

17-10-2024 Source: https://www.analyticsvidhya.com/blog/2018/04/introduction-to-graph-theory-network-analysis-python-codes/ 21

Social Network Analytics – Session 1

Banking Network
❑ Vertices – Account Holders
❑ Attributes – Name, Demographics, KYC, Products, Balance
❑ Edges – Transactions
❑ Attributes – Type, Amount, Authentication, Time, Location, Device

17-10-2024 Source: https://www.analyticsvidhya.com/blog/2018/04/introduction-to-graph-theory-network-analysis-python-codes/ 22

Social Network Analytics – Session 1

Social Network
❑ Vertices – Users
❑ Attributes – Name, Demographics, Connections, Likes, Subscription
❑ Edges – Interactions
❑ Attributes – Like, Comment, Direct Message, Time, Duration, Type
of Content, Topic

17-10-2024 Source: https://www.analyticsvidhya.com/blog/2018/04/introduction-to-graph-theory-network-analysis-python-codes/ 23

Social Network Analytics – Session 1

Supply Chain Network

❑ Vertices – Warehouses
❑ Attributes – Location, Size, Capacity, Storage Type, Connectivity
❑ Edges – Trucks
❑ Attributes – Load Capacity, Year of Make, Geographical Permit,
Maintenance Cost

17-10-2024 Source: https://www.analyticsvidhya.com/blog/2018/04/introduction-to-graph-theory-network-analysis-python-codes/ 24

Social Network Analytics – Session 1

Popular Real-world Networks

Social Network
• Telephone call network
• Email message network
• Film actor collaboration network
• Academic co-authorship network

Information Network
• World Wide Web (WWW)
• Citation network
Technological Network
• Electric power grids
• Networks of airline routes
• Network of Railway Routes
• Electronic circuits
• Delivery networks of post-office/Courier
• The Internet

Language Network
• Network formed by using the persons speaking a particular language

17-10-2024 Presented by Dr. Purva Grover 25

Social Network Analytics – Session 1

Some more: Key Application Areas

Healthcare
• Combating Epidemics
• Mass Vaccination
Social Media & E-Commerce
• Friend & Follow Recommendation
• Know Your Customers
• Recommendation & viral marketing
Web & Cyberspace
• Search engine optimization
• Malware detection
• Spam detection
Police & Military
• Fighting cyber crimes
• Fighting terrorism
• Network-centric warfare
Scientific Research & Academic Collaboration

17-10-2024 Presented by Dr. Purva Grover 26

Social Network Analytics – Session 1

SNA Applications: Healthcare

❑Modeling the spread of infectious
diseases
❑Contact tracing during epidemic
outbreak to identify possible patients
❑Identify and isolate super-spreaders
❑Planning lockdown schedule
❑Identify vulnerable population during
vaccination
❑Planning vaccination schedule, etc.

2003 SARS contact Network in Taiwan

https://doi.org/10.1007/978-1-4419-6892-0_15
17-10-2024 Presented by Dr. Purva Grover 27
Social Network Analytics – Session 1

SNA Applications: Social Media

❑Identifying friendship structures in online social media
❑Recommending friends, and groups, or pages to follow
❑Identifying information propagation patterns in social networks
❑ Designing Humanitarian response applications after large-scale crises,
etc.

17-10-2024 Presented by Dr. Purva Grover 28

Social Network Analytics – Session 1

SNA Applications: E-Commerce

❑Customer profiling to Know the customers
❑Product/Service recommendation based on customer profile
❑Instigating viral marketing by pinpointing influential players
❑“People like you buy”, “Frequently bought with this”, or “Frequently
browsed”, “Trending” are common buzzwords

17-10-2024 Presented by Dr. Purva Grover 29

Social Network Analytics – Session 1

SNA Applications: Web Search Optimization

❑ Ranking webpages based on hyperlinks
❑ Ordering of displayed pages based on
ranks
❑ Displaying webpages based on user
search profile

Google’s PageRank

17-10-2024 Presented by Dr. Purva Grover 30

Social Network Analytics – Session 1

SNA Applications: Cybercrimes & Terrorism

❑Online fraud, fake news propagation, cyber
bullying/trolling, sharing pornographic materials,
etc. rising with growth of social media
❑Terrorists often use social media to communicate
as well as to brainwash innocent people
❑These people often span across countries and use
untraceable communication devices
❑Tracking cyber criminals in conventional methods
are difficult due to user anonymity, fake accounts,
lack of cyber laws, etc. 9/11 Terrorist Network
http://www.orgnet.com/hijackers.html
❑Social network analysis techniques help nabbing
these criminals

17-10-2024 Presented by Dr. Purva Grover 31

Social Network Analytics – Session 1

SNA Applications: Organizational Network Analysis

❑Classic (linear) organization charts do not
effectively describe the real social network of
an organization
❑The informal networks, historically considered
an annoying problem and an indicator of
undisciplined attitude of workers, carry huge
potential if applied suitably
❑ ONA provides information on how to improve
performance in the organization.
❑ONA represents the complete set of real
relationships between the players: https://www.i4cp.com/productivity-blog/what-organizational-
❑Who is in touch with whom network-analysis-is-and-how-it-benefits-companies
❑Specific features of each player
❑Type and intensity of relationship, etc.

17-10-2024 Presented by Dr. Purva Grover 32

Social Network Analytics – Session 1

Problem Statement 1
Assume you are a manager in an organization. Draw a network which
you think will exist in your workplace.
For example:
1.If you are HR manager, then there is need for you to study
“Organizational Network Analysis” for improving organization
performance.
2.If you are a Head of customer care department, then there is need for
you to study “Word of mouth propagation from recent customers”
for getting new customers.
3.If you are “Head of Sales”, where to open new store?

17-10-2024 Presented by Dr. Purva Grover 33

Social Network Analytics – Session 1
References
❑Chakraborty, T. (2021). Social Network Analysis. Wiley India Pvt. Ltd.
❑https://www.analyticsvidhya.com/blog/2018/04/introduction-to-
graph-theory-network-analysis-python-codes/
❑Newman, M. (2010). Networks: an introduction. Oxford University
Press.

17-10-2024 Presented by Dr. Purva Grover 34

Social Network Analytics – Session 1

Thank you