lOMoARcPSD|212 559 03

UNIT-1: INTRODUCTION TO SOCIAL MEDIA ANALYTICS

Introduction to Social Media Analytics (SMA) - Social media landscape - Need for SMA -
SMA in Small organizations - SMA in large organizations - Application of SMA in different
areas - Network fundamentals and models: The social networks perspective - nodes, ties and
influencers - Social network and web data and its methods - Graphs and Matrices - Basic
measures for individuals and networks - Information visualization.

1. Introduction to Social Media Analytics (SMA)

Social media analytics is the process of collecting, measuring, and analyzing data
from social media platforms to understand and evaluate the performance of a brand or
organization's social media presence.

This process involves the use of various tools and techniques to extract, clean, and
transform data from social media platforms, such as Facebook, Twitter, Instagram, and
LinkedIn. The data collected can include metrics such as likes, shares, comments, followers,
and mentions, as well as text-based data such as comments and posts.

Once the data has been collected, it can be analyzed using a variety of methods and
techniques, including:

1. Descriptive analytics: Summarizing and describing the data, such as calculating the
number of followers or the average number of likes per post.

2. Diagnostic analytics: Identifying patterns and trends in the data, such as identifying
the most popular topics or the best time to post.

3. Predictive analytics: Using the data to make predictions about future behavior or
outcomes, such as forecasting the number of followers or predicting the success of a
future campaign.

4. Text mining and natural language processing: Extracting meaning from text-based
data, such as comments and posts, using techniques such as sentiment analysis, topic
modeling, and named entity recognition.

5. Social network analysis: Analyzing the structure and dynamics of interactions and
relationships on social media platforms, using techniques such as centrality measures,
community detection, and network statistics.

The insights and information obtained through social media analytics can be used to
inform and optimize social media strategy, improve the effectiveness of marketing and
advertising campaigns, and increase engagement and reach on social media platforms.

Social Media :
Websites and applications that enable users to create and share content or to participate in
social networking.
 lOMoARcPSD|212 559 03

Analytics means analysis of data

“The real impact of analytics means analysis and interpretation of data leads to actionable
insights.”
Social Media Analytics
“the art and science of extracting valuable hidden insights from vast amounts of semi
structured and unstructured social media data to enable informed and insightful decision
making”.

2. Social Media Landscape

Social media landscape shows how media's world is divided and which particular
media platforms are reigning supreme in the digital world at this moment. Social media
landscape. Connecting with customers and potential customers positively impacts your
relationship with customers, as well as increases brand loyalty.

The social media landscape:

Means Different platform and apps that enable people to connect and share in different
ways.
The social media landscape refers to the various social media platforms that exist and
the way they are used by different audiences and for different purposes.

Some of the most popular social media platforms include:

1. Facebook: The largest social network in the world, with over 2.7 billion monthly
active users. It is used for a variety of purposes, such as connecting with friends and
family, sharing news and information, and promoting businesses and brands.

2. YouTube: The world's second-largest search engine and the second most visited
website after Google. It is used primarily for watching and sharing videos, with
content ranging from music videos to educational content.

3. Instagram: A photo and video sharing platform with over 1 billion monthly active
users. It is known for its visual-based content, such as photos and videos, and its use
for influencer marketing, fashion and beauty industry, and personal branding.

4. Twitter: A micro-blogging platform with over 330 million monthly active users. It is
known for its short, text-based posts and its use for real-time news and information, as
well as for following and engaging with public figures and brands.
 lOMoARcPSD|212 559 03

5. LinkedIn: A professional networking platform with over 740 million members. It is

used for connecting with other professionals, finding job opportunities, and promoting
business and brand.

Each social media platform has its own unique features and audiences, and they are often
used in different ways. For example, Instagram is popular among younger users and is often
used to share photos and videos, while LinkedIn is more popular among working
professionals and is often used for networking and job searching.

It's important to note that social media landscape is ever-changing with new platforms
emerging and existing platforms evolving. Businesses and organizations need to stay updated
with the latest trends and updates to effectively use social media for their growth.

3. Need of Social Media Analytics

There are several reasons why social media analytics are important for businesses and
organizations:

1. Measurement of Success: Social media analytics allow businesses to measure the

success of their social media campaigns by tracking metrics such as engagement,
reach, and website traffic from social media. This helps them to identify what works
and what doesn't, and make data-driven decisions about their social media strategy.

2. Understanding the Audience: Social media analytics provide insights into the
demographics, interests, and behaviors of a business's social media audience. This
information can be used to tailor content and campaigns to better engage and attract
the target audience.

3. Identifying Trends and Insights: Social media analytics can be used to identify
trends and insights that can inform a business's overall marketing strategy. For
example, by tracking conversations and sentiment around a brand or industry,
businesses can stay informed about what people are saying and adjust their approach
accordingly.

4. Competitive Analysis: Social media analytics can be used to track the performance
of competitors, which can help businesses stay ahead of the curve and make data-
driven decisions about their own social media strategy.

5. Cost-effective Marketing: Social media analytics can help businesses identify which
platforms and campaigns are most cost-effective, allowing them to allocate resources
more efficiently and maximize ROI.

Overall, social media analytics are essential for businesses and organizations to stay
competitive and make data-driven decisions about their social media strategy, by
 lOMoARcPSD|212 559 03

understanding the audience and competitors, tracking the performance of their campaigns and
identifying trends and insights.

• To Know the Best time to share

• To create the best content(tutorial or ad video)
• To know the best social media networks
• To Know what people say about business
• To better understand Competitors
• To Create better social media marketing strategies.

4. SMA in Small organizations - SMA in large organizations

Social media analytics (SMA) can be beneficial for both small and large organizations,
although the specific ways in which they use SMA may differ.

Small organizations often have limited resources and may use SMA to:

 Identify their target audience

 Track their competitors

 Measure the success of their campaigns

 Identify cost-effective marketing

 Identifying potential business opportunities

Large organizations, on the other hand, may have more resources and may use SMA in ways
such as:

 Tracking performance across multiple departments and campaigns

 Identifying trends and insights to inform overall business strategy

 Monitoring and managing the company's brand reputation

 Optimizing their advertising and promotions

 Identifying new business opportunities and markets

In both cases, SMA can be a valuable tool as it allows organizations to make data-driven
decisions about their social media strategy, understand their target audience and identify
potential business opportunities, all while maximizing their resources and ROI.
 lOMoARcPSD|212 559 03

5. Applications of Social Media Analytics

Social media analytics is the process of collecting, measuring, and analyzing data
from social media platforms to understand and inform business decisions.

Some common applications of social media analytics include:

1. Marketing and advertising: Identifying trends and consumer preferences to inform

targeted advertising and marketing campaigns.

2 .Brand monitoring: Tracking mentions of a brand or company across social media to

understand public perception and identify potential issues.

3. Customer service: Identifying customer complaints and feedback on social media to

improve customer service and support.

4. Competitive intelligence: Tracking competitors' social media activity to understand their

strategies and identify areas for improvement.

5. Crisis management: Monitoring social media to identify potential crises and respond
quickly to mitigate damage.

6 .Product development: Using social media data to inform product development decisions
and identify new product opportunities.

7. Sales: Using social media data to generate leads and track the success of sales campaigns.

Here are some examples of how businesses and organizations use social media analytics:

 A retail company uses social media analytics to track mentions of their brand and
products on social media. They use this data to understand consumer preferences and
identify popular products, which they then feature in their advertising and marketing
campaigns.
 A fast-food chain uses social media analytics to track customer complaints and
feedback on their social media channels. They use this data to improve their customer
service and support, and to identify and address any issues with their products or
services.
 A political campaign uses social media analytics to track mentions of their candidate
and their opponents on social media. They use this data to understand public
perception and identify potential areas of concern, which they then address in their
messaging and advertising.
 A sports team uses social media analytics to track mentions of their team and players
on social media. They use this data to understand fan sentiment and identify potential
areas of concern, which they then address in their social media and marketing
campaigns.
 A music festival uses social media analytics to track mentions of their festival and
competing festivals on social media. They use this data to understand public
 lOMoARcPSD|212 559 03

perception and identify potential areas of concern, which they then address in their
messaging and advertising.
 A media company uses social media analytics to track mentions of their shows and
personalities on social media, they use this data to identify the most popular shows
and personalities in order to invest more resources in them.
 A hotel chain uses social media analytics to track mentions of their brand on social
media, they use this data to identify potential customer needs and create targeted
campaigns to meet those needs, resulting in increased bookings.

There are various social media analytics tools available that can help you track and measure
the performance of your social media campaigns and presence. Some popular examples
include:

• Brand watch

• Google Analytics

• Channelview Insights

• Talkwalker

• Mentionlytics

Brand watch

• Track and analyze data from many sources including blogs, forums, and review sites ,
as well as social networks.

• Find meaning in the billions of conversations happening online

• Paid tool

• Used by communication teams ,social media marketers who focus on engagement and
brand monitoring.

Google Analytics

• Track the traffic and leads to your website from social media channels

• A web analytics service offered by google that tracks and reports website traffic.

• Free tool

• Can be used by all

Channelview Insights

• Analyze the YouTube performance of multiple channels

• Paid tool
 lOMoARcPSD|212 559 03

Talkwalker

• Best for Social media managers who run a YouTube channel alongside other social
channels.

• Monitor Conversions from more than 150 million sources to analyze engagement
,potential reach,comments,sentiment, and emotions

• Paid tool

Mentionlytics

• Track mentions, keywords, and sentiment across multiple languages on social

channels and elsewhere on the web.

• Paid tool.

6. Network fundamentals and models

Network fundamentals and models in social media analytics are used to understand
the underlying structure and dynamics of social media platforms and how they affect user
behavior and the spread of information. These models allow analysts to identify key
influencers, communities, and patterns in user behavior and interactions, and to understand
how information spreads through the network.

A network is a group of two or more computers or other electronic devices that are
interconnected for the purpose of exchanging data and sharing resources

Some examples of network fundamentals and models used in social media analytics include:

1. Social Network Analysis (SNA): SNA is used to map and analyze the connections
between users on a social media platform. It can be used to identify key influencers
and communities, and to measure the flow of information within the network.

2. Graph Theory: Graph theory is used to model the networks formed by users and the
relationships between them on a social media platform. It can be used to identify
patterns and trends in user behavior and interactions, and to understand how
information spreads through the network.

3. Network Centrality Measures: These measures are used to identify key influencers,
opinion leaders, and communities on a social media platform. They can be used to
target specific groups of users with marketing or advertising campaigns, or to identify
which users are most likely to spread information through the network.

4. Community Detection Algorithms: These algorithms are used to identify groups of

users who share similar interests or behaviors on a social media platform. They can be
used to segment audiences and tailor content or campaigns to specific groups of users.
 lOMoARcPSD|212 559 03

5. Content Propagation Models: These models are used to understand how information
spreads through a social media platform. They can be used to predict how likely a
message is to be shared, who is likely to share it, and how far it is likely to spread.

Social Network: Nodes, Ties & Influencer

A social network is a term used to describe a variety of platforms, applications, and

technologies that allow people to interact socially with others over the web.
Examples:
Facebook, YouTube, Twitter, Instagram, blogs, and other sites that have content based
on user engagement and user-generated content (UGC).

The social networks perspective is a way to understand the structure and dynamics of
social interactions and relationships. It focuses on the connections between individuals or
groups, known as ties, and the individuals or groups themselves, known as nodes.

From a social networks perspective, nodes represent the actors in a network (e.g.,
individuals, organizations, or groups) and ties represent the relationships between them (e.g.,
friendships, collaborations, or interactions). This approach allows for the examination of the
patterns and dynamics of these connections, and how they affect the behavior and outcomes
of the nodes.

Influencers in social networks are the actors who have more ties than others, or who have
more central positions in the network. They are considered as key players in spreading
information, ideas, and influence across the network.

Nodes
• The things that are connected are called Nodes,Vertices,Entities.
• It can be people ,Computer,countries etc.
• Also represent contents:
o Web pages, Keyboard, videos etc.
• It represent physical or virtual location or events .
• Nodes are building block of network.
Ties
• The connection between nodes are called ties or Edge and links.
• They are the relationship between nodes:
– Friendship,trading,agreement,shared attributes,transactions etc.
• It can be association/affiliation, formal relationship, biological relationship etc

Directed Edge(asymmetric edge)

- Have a clear origin and destination
- Twitter user follows another user,
- Email is sent to a recipient.
Undirected Edge(Symmetric edge)
- Two facebook users are friends
Influencer
• A person who has the power to influence many people as through social media or
traditional media.
• Influencers in social media are people who have built a reputation for their
 lOMoARcPSD|212 559 03

knowledge and expertise on a specific topic. They make regular posts about that topic
on their preferred social media channels and generate large followings of enthusiastic,
engaged people who pay close attention to their views.
Influencers Types
• Mega Influencers – Have more than 1 million followers
• Macro Influencers – 40,000 to 1 million followers
• Micro Influencers – 1,000 to 40,000 followers
• Nano Influencers – Below 1,000 followers
Level of influence
• Celebrities
• Key Opinion Leader – Journalist,Industry Expert,Professionals

Web Data
Web data refers to the information that is available on the internet, including text,
images, videos, and other types of content. It can be collected from various sources such as
websites, social media platforms, blogs, forums, and online communities.

Web data can be collected in a variety of ways, including web scraping, APIs, and
manual data entry. It is then typically cleaned, transformed, and analyzed using various tools
and techniques such as data visualization, text mining, and machine learning.

Methods used to extract, analyze and interpret social network and web data include:

1. Web scraping: Collecting data from the Internet by automating the process of visiting
websites and extracting information.

2. Network visualization: Representing the nodes and ties in a network graphically,

using software such as Gephi, Cytoscape, or NodeXL.

3. Social network analysis (SNA): Analyzing the structure and dynamics of a network,
using techniques such as centrality measures, community detection, and network
statistics.

4. Text mining and natural language processing: Extracting meaning from text-based
data, such as comments, tweets, and posts, using techniques such as sentiment
analysis, topic modeling, and named entity recognition.

5. Machine learning: Applying algorithms to learn patterns in data and make

predictions or classifications, such as identifying key influencers or predicting the
spread of information in a network.

Web Data

- Data that is sourced and structured from websites

- Means the data and any content made available on publicly accessible networks
> Data on YouTube,Facebook or any other websites.
 lOMoARcPSD|212 559 03

7. Graphs and Matrices

Graphs and matrices are commonly used in social media analytics to represent and
analyze data from social media platforms.

Graph:

A graph is a mathematical representation of a network of objects, where the objects

are represented by vertices (or nodes) and the connections between them are represented by
edges.

In social media analytics, nodes can represent users, accounts, or pages, and edges
can represent relationships, such as following or friendship. Graphs can be used to analyze
the structure and dynamics of social media networks, such as identifying central nodes,
communities, and patterns of interaction.

A graph is a collection of nodes and edges

⚫ Denoted by G = (V, E).
V = nodes (vertices, points).
E = edges (links, arcs) between pairs of nodes.
Graph size parameters: n = |V|, m = |E|.

• V:={1,2,3,4,5,6}

• E:={{1,2},{1,5},{2,3},{2,5},{3,4},{4,5},{4,6}}

Simple graphs are graphs without multiple edges or self-loop.

 lOMoARcPSD|212 559 03

Complete Graph: Let G be simple graph on n vertices. If the degree of each vertex is (n-1)
then the graph is called as complete graph.
Complete graph on n vertices, it is denoted by Kn.
In complete graph Kn, the number of edges are
(every node is connected with every other node)

Bipartite Graph:
The graph is called as bipartite graph, if their vertexes set V can be partitioned into two
distinct subset say V1 & V2. such that V1 U V2=V & V1  V2 =  & also each edge of G
joins a vertex of V1 to vertex of V2.
A graph can not have self loop.

Matrix:

A matrix is a rectangular array of numbers or other data, often used to represent data
in a tabular format.

Matrix Representation of Graphs

A graph can also be represented by matrix.

Two ways are used for matrix representation of graph are given as follows,

1. Adjacent Matrix

2. Incident Matrix

Matrices can be used to represent various types of data, such as user-item interactions,
content, or sentiment.

 For example, a user-item interaction matrix can be used to represent the

interactions between users and items on a social media platform, such as likes, shares,
or comments. Each row of the matrix represents a user, and each column represents an
item. The cells of the matrix contain the interaction data, such as a 1 if a user has liked
an item, and a 0 if they haven't.
 Another example is a content matrix, which can be used to represent the content of
posts or tweets. Each row of the matrix represents a post or tweet, and each column
represents a word or phrase. The cells of the matrix contain the frequency of the word
or phrase in the post or tweet.
 Sentiment matrix can be used to represent the sentiment of posts or tweets. Each row
of the matrix represents a post or tweet, and each column represents a sentiment label
 lOMoARcPSD|212 559 03

(positive, neutral, negative). The cells of the matrix contain the sentiment score of the
post or tweet.

Matrices are powerful tools for representing and analyzing social media data, and can be
used to gain insights into various aspects of social media, such as user interactions, content,
and sentiment.

There are several basic measures that can be calculated for individuals and networks
using graphs and matrices in social media analytics.

For individuals:

 Degree: The number of edges incident to a node (i.e. the number of connections a user
has)

 Closeness centrality: A measure of how close a node is to all other nodes in a network

 Betweenness centrality: A measure of the extent to which a node lies on the shortest
path between other nodes

 Eigenvector centrality: A measure of the relative importance of a node in a network,

based on the principle that important nodes are connected to other important nodes

For networks:

 Density: The proportion of edges present in a network relative to the total number of
possible edges

 Clustering coefficient: A measure of the degree to which a network is clustered, or

how likely it is that two people who are connected to the same person are also
connected to each other.

 Connectedness: A measure of the connectivity of a network, or the extent to which all

nodes are connected to each other

 Modularity: A measure of the degree to which a network can be divided into distinct
communities or groups

These measures can be calculated using various tools, such as Python libraries like
NetworkX or Gephi, and can be used to gain insights into the structure and dynamics of
social media networks. For example, degree centrality can be used to identify key influencers
in a network, while density can be used to measure the overall connectivity of a network.
lOMoARcPSD|212 559 03
lOMoARcPSD|212 559 03
 lOMoARcPSD|212 559 03

Isomorphism

Definition: Two graphs are thought of as equivalent (called isomorphic) if they have
identical behavior in terms of graph theoretic properties.

Two graphs G(V, E) & G’(V’,E’) are said to be isomorphic to each other if there is one-one
correspondence between their vertices & between their edges such that incidence relationship
in preserved.

It is denoted by G1=G2

8. Information Visualization

Information visualization, also known as data visualization or simply visualization, is

the practice of representing data in a graphical or visual format to facilitate understanding and
analysis. In the context of social media analytics, information visualization is used to present
large and complex datasets in a way that is easy to understand and interpret.

There are many different types of information visualizations that can be used in social
media analytics, including:

 Bar charts: Used to compare the frequencies or values of different categories

 lOMoARcPSD|212 559 03

 Line charts: Used to show changes in a variable over time

 Pie charts: Used to show the proportion of different categories in a dataset

 Scatter plots: Used to show the relationship between two or more variables

 Heat maps: Used to show the intensity of a variable across different areas or regions
 lOMoARcPSD|212 559 03

 Network diagrams: Used to show the connections between different entities in a

network

 Word clouds: Used to show the most common words or phrases in a dataset

These visualizations can be used to uncover patterns and trends in social media data,
and can be used to answer various questions related to topics such as sentiment analysis, user
engagement, and content analysis.

It's important to note that information visualization is an art as well as a science, as the
choice of visualization type depends on the data and the question you're trying to answer.
Moreover, the design and layout of visualizations also play an important role in how
effectively the information is communicated.

In summary, information visualization is an important tool in social media analytics, as

it allows analysts to communicate complex data in an easy-to-understand format, and can be
used to uncover patterns and trends in social media data.