Shivajirao S Jondhale College of Engineering, Dombivli (E)

Department of Computer Engineering

Experiment No. 1

Aim: To study various Social Media platforms, Social Media analytics tools,
Social Media Analytics techniques and engagement metrics, Applications of Social
media analytics for business.

Theory:
A. Social media platforms:-
Social media are interactive media technologies that facilitate the creation and
sharing of information, ideas, interests, and other forms of expression through
virtual communities and networks. While challenges to the definition of social
media arise due to the variety of stand-alone and built-in social media services
currently available, there are some common features:

 Social media are interactive Web 2.0 Internet-based applications.

 User-generated content—such as text posts or comments, digital photos or
videos, and data generated through all online interactions—is the lifeblood
of social media.
 Users create service-specific profiles for the website or app that are
designed and maintained by the social media organization.
 Social media helps the development of online social networks by
connecting a user's profile with those of other individuals or groups.
Benefits of social media:

 Faster, Easier Communication

 Social Makes Your Brand More Relatable
 Social is Great for Promoting Content
 Reputation Management
 Generate Leads Directly & Indirectly
B. Social Media analytics tools:-
Social media analytics is the ability to gather and find meaning in data gathered
from social channels to support business decisions and measure the performance of
actions based on those decisions through social media.

SMA Lab/VIII 1
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
Social media analytics is broader than metrics such as likes, follows, retweets,
previews, clicks, and impressions gathered from individual channels. It also differs
from reporting offered by services that support marketing campaigns such as
LinkedIn or Google Analytics.
Social media analytics uses specifically designed software platforms that work
similarly to web search tools. Data about keywords or topics is retrieved through
search queries or web ‘crawlers’ that span channels. Fragments of text are returned,
loaded into a database, categorized and analyzed to derive meaningful insights.

What Does Social Media Analytics Tools Mean?

In terms of sales, tools show how well a social media marketing campaign is going
by showing all positive turnovers or purchases that come directly from social
media sources such as Facebook and Twitter. These sites are useful for
disseminating purchase or signup links and correlate directly to traffic which can
be picked up by a specific social media analytics tool. For brand recognition and
sentiment analysis, some tools are able to mine the data from social networking
sites in order to find or discover the sentiment of people towards a brand or
business through methods such as natural language processing and pattern
recognition.
Examples of social media analytics tools or platforms:

 Google Analytics
 Twitter Analytics
 Facebook Insight
 Hootsuite
C. Social Media Analytics techniques and engagement metrics:-
In Social Analytics reports we display data as it comes from the various social
channel's APIs.
As there are many different types of data, understanding these can be difficult and
it may appear to vary from tool to tool or even from the native channels. Rest
assured that our data is accurate, and there is usually an explanation for any
apparent data discrepancies.
If you'd like to learn the definitions for the metrics within Owned Social Analytics,
check out our dedicated article here.
In Social Analytics there are three different types of data:

 Page level data accounts for actions taken on the page during a time frame.
SMA Lab/VIII 2
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

 Post level data is lifetime values specific to actions taken on those posts.
 Member data are the demographics and audience location data points and
widgets.
In Social Analytics, most metrics, such as the overview cards at the top and graphs
showing data over time, are based on Page level data. For example, Total
Impressions is the total number of impressions on any post on the page during the
time frame.

What are social media metrics?

Social media metrics are the data points that show you how well your social media
strategy is performing.
Helping you understand everything from how many people see your content all the
way through to how much money you earn from social media, metrics are the
building blocks for ongoing improvement and growth.
The most important social media metrics
1. Reach
2. Impressions

3. Audience growth rate

4. Engagement Rate
5. Amplification rate
6. Virality rate
7. Video views
8. Video completion rate
9. Customer satisfaction (CSAT) score

10. Net promoter score (NPS)

11. Click-through rate (CTR)
12. Conversion rate
13. Cost-per-click (CPC)
14. Cost per thousand impressions (CPM)
15. Social share of voice (SSoV)
SMA Lab/VIII 3
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
16. Social sentiment

D. Applications of Social media analytics for business.:-

Google Analytics:
Google Analytics is a web analytics service offered by Google that tracks and
reports website traffic, currently as a platform inside the Google Marketing
Platform brand. Google launched the service in November 2005 after acquiring
Urchin.
As of 2019, Google Analytics is the most widely used web analytics service on the
web. Google Analytics provides an SDK that allows gathering usage data from iOS
and Android app, known as Google Analytics for Mobile Apps. Google Analytics
can be blocked by browsers, browser extensions, firewalls and other means.
Google Analytics is used to track website activity such as session duration, pages
per session and the bounce rate of individuals using the site, along with the
information on the source of the traffic. It can be integrated with Google Ads,[9]
with which users can create and review online campaigns by tracking landing page
quality and conversions (goals). Goals might include sales, lead generation,
viewing a specific page, or downloading a particular file. Google Analytics'
approach is to show high-level, dashboard-type data for the casual user, and more
in-depth data further into the report set. Google Analytics analysis can identify
poorly performing pages with techniques such as funnel visualization, where
visitors came from (referrers), how long they stayed on the website and their
geographical position. It also provides more advanced features, including custom
visitor segmentation. Google Analytics e-commerce reporting can track sales
activity and performance. The e-commerce reports show a site's transactions,
revenue, and many other commerce-related metrics.

How Google Analytics works

Google Analytics is a platform that collects data from your websites and apps to
create reports that provide insights into your business.

Measuring a website
To measure a website, you first have to create a Google Analytics account. Then
you need to add a small piece of JavaScript measurement code to each page on
your site. Every time a user visits a webpage, the tracking code will collect
pseudonymous information about how that user interacted with the page.

SMA Lab/VIII 4
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
For the Google Store, the measurement code could show how many users visited a
page that sells drinkware versus a page that sells houseware. Or it could tell us how
many users bought an item like an Android doll by tracking whether they made it
to the purchase-confirmation page.
The measurement code will also collect information from the browser like the
language setting, the type of browser (such as Chrome or Safari), and the device
and operating system on which the browser is running. It can even collect the
“traffic source,” which is what brought users to the site in the first place. This
might be a search engine, an advertisement they clicked on, or an email marketing
campaign.

Processing and reporting

When the measurement code collects data, it packages that information up and
sends it to Google Analytics to be processed into reports. When Analytics
processes data, it aggregates and organizes the data based on particular criteria like
whether a user’s device is mobile or desktop, or which browser they’re using.
But there are also configuration settings that allow you to customize how that data
is processed. For example, you might want to apply a filter to make sure your data
doesn’t include any internal company traffic or developer traffic.

Once Analytics processes the data, it’s stored in a database where it can’t be
changed.
So remember, when you set up your configuration, don’t exclude any data you
think you might want to analyze later. Once the data has been processed and stored
in the database, it will appear in Google Analytics as reports.

Screenshots:

1. Home Page with Demo Account

SMA Lab/VIII 5
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

2. Report Snapshot:Acquisition

3. Traffic acquisition

SMA Lab/VIII 6
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

4. Engagement :Conversions

[Link]: Publisher ads

SMA Lab/VIII 7
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

6. Demographic Details:

CONCLUSION: -
In this experiment we learnt about various Social Media platforms, Social Media
analytics tools, Social Media Analytics techniques and engagement metrics,
Applications of Social media analytics for business.

SMA Lab/VIII 8
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 2

AIM: Perform the following:

Data Collection,connect to and capture social media data for business
( scraping,crawling,parsing) for structured data.

THEORY:
Social media data is any type of data that can be gathered through social media. In
general, the term refers to social media metrics and demographics collected
through analytics tools on social [Link] media data can also refer to data
collected from content people post publicly on social media. Social media data
collection can help you customize your social media marketing strategy for each
social network. Even more specifically, you can customize your strategy by
location or demographics.
Some of the most important raw data you can collect through social media:

 Engagement: Clicks, comments, shares, etc.

 Reach
 Impressions and video views
 Follower count and growth over time
 Profile visits
 Brand sentiment
 Social share of voice
 Demographic data: age, gender, location, language, behaviors, etc.
1. Web Scraping:
Web Scraping is a technique used to extract a large amount of data from websites
and then saving it to the local machine in the form of XML, excel or SQL. The
tools used for web scraping are known as web scrapers. On the basis of the
requirements given, they can extract the data from any website in a fraction of
time. This automation of tasks is very helpful for developing data for machine
learning and other purpose. They work in four steps:

 Sending the request to the target page.

SMA Lab/VIII 9
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

 Getting response from the target page.

 Parsing and extracting the response.
 Download the data.
Some of the popular web scraping tools are ProWebScraper, [Link], etc.

2. Web Crawling:
Web Crawling is analogous to a spider crawling but the place of crawling here is
the web!. It basically visits a website and read web pages for the purpose of
building entries for search engine index. The tools that are used for web crawling
are known as web crawlers or spiders. A series of web pages are analyzed and links
to the pages on them are then followed for even more links thus it does a deep
search for extracting of information. Famous search engines such as Google,
Yahoo and Bing do web crawling and use this information for indexing web pages.
Examples are Scrapy and Apache nut.

3. Data Parsing:
Data parsing is converting data from one format to another. Widely used for data
structuring, it is generally done to make the existing, often unstructured, unreadable
data more comprehensible.

Data parsing is a widely used method for data structuring; thus, you may discover
many different descriptions while trying to find out what exactly it is. To make
understanding this concept easier, we’ve put it into a simple definition.

What is data parsing?

Data parsing is a method where one string of data gets converted into a different
type of data. So let’s say you receive your data in raw HTML, a parser will take the
said HTML and transform it into a more readable data format that can be easily
read and understood.
CONCLUSION: Hence we have successfully studied and demonstrated Data
collection,connect to and capture social media data for business

SMA Lab/VIII 10
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
( scraping,crawling,parsing) for structured data.

SMA Lab/VIII 11
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 3

AIM:Perform the following:

Data Cleaning and Storage- Preprocess, filter and store social media data for
business using Python for unstructured data.
(Analysis of Twitter data: Budget 2023 )

THEORY:
What is data cleaning?
Data cleaning is the process of fixing or removing incorrect, corrupted, incorrectly
formatted, duplicate, or incomplete data within a dataset. When combining multiple
data sources, there are many opportunities for data to be duplicated or mislabeled.
If data is incorrect, outcomes and algorithms are unreliable, even though they may
look correct. There is no one absolute way to prescribe the exact steps in the data
cleaning process because the processes will vary from dataset to dataset. But it is
crucial to establish a template for your data cleaning process so you know you are
doing it the right way every time.
While the techniques used for data cleaning may vary according to the types of
data your company stores, you can follow these basic steps to map out a framework
for your organization.

Step 1: Remove duplicate or irrelevant observations

Remove unwanted observations from your dataset, including duplicate
observations or irrelevant observations.

Step 2: Fix structural errors

Structural errors are when you measure or transfer data and notice strange naming
conventions, typos, or incorrect capitalization. These inconsistencies can cause
mislabeled categories or classes.

Step 3: Filter unwanted outliers

Often, there will be one-off observations where, at a glance, they do not appear to
fit within the data you are analyzing. If you have a legitimate reason to remove an
outlier, like improper data-entry, doing so will help the performance of the data you
are working with.

Step 4: Handle missing data

There are a couple of ways to deal with missing data. Neither is optimal, but both
can be considered.
SMA Lab/VIII 12
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
 As a first option, you can drop observations that have missing values, but
doing this will drop or lose information, so be mindful of this before you
remove it.
 As a second option, you can input missing values based on other
observations; again, there is an opportunity to lose integrity of the data
because you may be operating from assumptions and not actual
observations.
 As a third option, you might alter the way the data is used to effectively
navigate null values.
Step 5: Validate and QA
At the end of the data cleaning process, you should be able to answer these
questions as a part of basic validation:

In this experiment we are going to collect unstructured data from twitter tweets,
store it, perform variouscleansing operations, preprocessit and do the further
sentiment analysis on filtered tweets.
Twitter is an online social media and social networking service owned and
operated by American companyTwitter, Inc., on which users post and reply to
texts, images and videos known as "tweets".Registered users cantweet, like,
'retweet' tweets and direct message (DM), while unregistered users only have the
ability to viewpublic tweets. Users interact with Twitter through browser or mobile
frontend software, or programmatically viaits APIs.
Tweets are publicly visible by default, but senders can restrict message delivery to
only their followers. Userscan mute users they do not wish to interact with, block
accounts from viewing their tweets, and removeaccounts from their followers list
Users can tweet via the Twitter website, compatible external applications(such as
for smartphones), or by Short Message Service (SMS) available in certain
[Link] maysubscribe to other users' tweets—this is known as "following"
and subscribers are known as "followers" or"tweeps",

Following python libraries are used :

snscrape :
snscrape is a scraper for social networking services (SNS). It scrapes things like
user profiles, hashtags, orsearches and returns the discovered items, e.g. the
relevant posts.

SMA Lab/VIII 13
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
Using snscrape, the services supported for Twitter are : users, user profiles,
hashtags, searches (live tweets, toptweets, and users), tweets (single or surrounding
thread), list posts, communities, and trends.
snscrape requires Python 3.8 or higher. The Python package dependencies are
installed automatically when youinstall snscrape.
nltk:
Natural Language Toolkit is a leading platform for building Python programs to
work with human languagedata. It provides easy-to-use interfaces to over 50
corpora and lexical resources such as WordNet, along with asuite of text processing
libraries for classification, tokenization, stemming, tagging, parsing, and
semanticreasoning,NLTK is available for Windows, Mac OS X, and Linux. It is
one of the most used libraries for naturallanguage processing and computational
linguistics
textblob:

TextBlob is a Python (2 and 3) library for processing textual data. It provides a

simple API for diving intocommon natural language processing (NLP) tasks such
as part-of-speech tagging, noun phrase extraction,sentiment analysis, classification,
translation, and more.:
os:
The OS module in Python provides functions for interacting with the operating
system. OS comes underPython’s standard utility modules. This module provides a
portable way of using operating system-dependentfunctionality.

Procedure to conduct Sentiment Analysis on Twitter tweets (Union Budget):

1. Import and install various python libraries as stated above.
2. By using :

[Link]("snscrape --jsonl --max-results 5000 --since 2023-01-31 twitter-

search'Budget 2023 until:2023-02-07'>[Link]")

Specify maximum results (5000),start date to end date and twitter search topic
(Budget2023),fetch records and store using [Link]
3. Read and display the fetched records by using:

tweetsdf = [Link]("[Link]" ,lines=True)

SMA Lab/VIII 14
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
[Link](5)
4. Use :[Link]() to write object to a comma-separated values (csv) file

5. Perform Data cleaning and preprocessing activities by dropping

unnecessarycolumns.(Originally 30 columns,after dropping 11 columns)
df1 = tweetsdf[[ 'date', 'rawContent' , 'renderedContent' , 'user' ,
'replyCount','retweetCount' , 'likeCount' , 'lang' , 'place' , 'hashtags' ,
'viewCount']].copy()
6. Drop duplicate records :

df1=[Link]("renderedContent")
So, it becomes :[4786 rows x 11 columns]
7. Remove unnecessary characters by defining function
punct = ['%','/',':','\\','&amp','&',';','?']
def removepunctuations(text):
for punctuation in punct:

text = [Link](punctuation,'')
return text
8. Display and plot graphs for most common words by using TfidfVectorizer,
CountVectorizer

9. Perform sentiment analysis on preprocessed tweets by using :

def getsubjectivity(text):
return TextBlob(text).[Link]
def get_polarity(text):
return TextBlob(text).[Link]
When a sentence is passed into Textblob it gives two outputs, which are polarity
andsubjectivity. Polarity is the output that lies between [-1,1], where -1 refers to
negativesentiment and +1 refers to positive sentiment. Subjectivity is the output
that lies within [0,1]and refers to personal opinions and judgments
10. Count and plot the graph showing the number of positive,negative and neutral
sentimentstextblobdf["textblobsentiment"].valuecounts()
SMA Lab/VIII 15
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

CONCLUSION: Hence, we have successfully studied and demonstrated Data

Cleaning and Storage- Preprocess filter and store social media data for business
using Python for unstructured data.

SMA Lab/VIII 16
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 4

AIM: To study and demonstrate Exploratory Data Analysis and visualization of

Social Media Data for business.

THEORY:
What is Exploratory Data Analysis?
We can define exploratory data analysis as the essential data investigation process
before the formal analysis to spot patterns and anomalies, discover trends, and test
hypotheses with summary statistics and visualizations. It gives an idea about the
data we will be digging deep into while analyzing. It aids in formulating how we
can handle data during analysis, like choosing models, handling outliers, deciding
model accuracy parameters, etc. Visualization helps to infer insights easily from
massive datasets.

Types of Exploratory Data Analysis

1. Univariate Plots
Univariate plots show the frequency or the distribution shape of a variable.

2. Histograms
Histograms are two-dimensional plots in which the x-axis divide into a range of
numerical bins or time intervals. The y-axis shows the frequency values, which are
counts of occurrences of values for each bin. Bar graphs have gaps between the
bars to indicate that they compare distinct groups, but there are no gaps in
histograms. Hence, They tell us if the distribution is left/positively skew (most of
the data falls to the right side), right/negatively skewed (most of the data falls to the
left side), bi-modal (graphs having two distinct peaks), normal (perfectly
symmetrical without skew), or uniform (almost all the bins have similar
frequency).

SMA Lab/VIII 17
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Probability Distribution Plots

Probability distributions are mathematical functions that describe all the possible
values that a random variable can assume within a given range. They help model
random phenomena, allowing us in order to estimate the probability of a particular
event. This type of distribution is helpful to know the likely outcomes and the
spread of potential values.

For a single random variable, probability distributions can be divided into two
types:

1. Discrete Probability Distributions for Discrete Variables

2. Binomial Distribution
Run Sequence Plots
A run chart, also known as a run-sequence plot, displays observed data in a time
sequence. So, Often, the data displayed represents some aspect of a business
process’s output or performance. It is, therefore, a form of a line chart. They are
often analyzed in order to locate anomalies in data that suggest shifts in a process
over time. Changes in location and scale and outliers can easily be detected.

Bivariate Plots
Bivariate plots display the relationship between two variables in exploratory data
analysis.
Bar Graphs
Bar charts can be used to compare nominal or ordinal data. They are helpful for
recognizing trends.

SMA Lab/VIII 18
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Scatter Plots
Scatter plots are commonly used in statistical analysis in order to visualize
numerical relationships. So, They are use in order to determine whether two
measures are correlate by plotting them on the x and y-axis. They are suitable for
recognizing trends.
For instance, you can see a scatter plot of two measures in the figure – the house’s
area against price and the trend line. The data points are concentrated in the lower
price and lower area range. A few outliers are indicating larger area houses
available for lower prices.

Box Plots
These charts show the distribution of values along an axis. Rectangular boxes are
used in order to bucket the data, giving us an idea of how the data points are spread
out. These boxes are also called quartiles which represent a quarter of a data set.
Boxes can be drawn vertically or horizontally.

SMA Lab/VIII 19
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
Box plots are suitable for identifying outliers. The below figure shows the structure
of a box plot.

Heat Maps
For instance, correlation heat maps show the interrelationship between variables—
areas as shaded as per the data’s values. So, Color differences can easily spot
similar and different values and make sense of the data variation. They are usually
helpful when you have a large amount of data. They are used during A/B testing to
see which parts of a web page are accessed by users on a website.

CONCLUSION: Hence, we have successfully studied and demonstrated

Exploratory Data Analysis and visualization of Social Media Data for business.

SMA Lab/VIII 20
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 5

AIM:ToDevelop Content based social media analytics model for business.

THEORY:
What Is Topic Analysis?
Topic analysis (also called topic detection, topic modeling, or topic extraction) is
a machine learning technique that organizes and understands large collections of
text data, by assigning “tags” or categories according to each individual text’s
topic or [Link] analysis uses natural language processing (NLP) to break
down human language so that you can find patterns and unlock semantic
structures within texts to extract insights and help make data-driven
[Link] two most common approaches for topic analysis with machine
learning are NLP topic modeling and NLP topic classification.

What Is Trend Analysis?

Trend analysis is a technique used in technical analysis that attempts to predict
future stock price movements based on recently observed trend data. Trend
analysis uses historical data, such as price movements and trade volume, to
forecast the long-term direction of market sentiment.

What is sentiment analysis (opinion mining)?

Sentiment analysis, also referred to as opinion mining, is an approach to natural
language processing (NLP) that identifies the emotional tone behind a body of
text. This is a popular way for organizations to determine and categorize opinions
about a product, service, or idea. It involves the use of data mining, machine
learning (ML) and artificial intelligence (AI) to mine text for sentiment and
subjective information.

Audio, video, image analytics:

Image analysis or imagery analysis is the extraction of meaningful information
from images; mainly from digital images by means of digital image
processing techniques. Image analysis tasks can be as simple as reading bar
coded tags or as sophisticated as identifying a person from their [Link]
content analysis or video content analytics (VCA), also known as video
analysis or video analytics (VA), is the capability of automatically
analyzing video to detect and determine temporal and spatial [Link]
technical capability is used in a wide range of domains including
entertainment, video retrieval and video browsing, health-care, retail, automotive,

SMA Lab/VIII 21
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
transport, home automation, flame and smoke detection, safety, and
security. The algorithms can be implemented as software on general-purpose
machines, or as hardware in specialized video processing units.

CONCLUSION: Hence, we have successfully studied and demonstrated to

Develop Content based social media analytics model for business.

SMA Lab/VIII 22
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 6

AIM:Develop Structure based social media analytics model for any business.
( e.g. Structure Based Models -community detection, influence analysis)
Analysis of Facebook data

THEORY:
Structured analytics in social media is the process of discovering
the structure of the relationships emerging from this social media use. It focuses on
identifying the users involved, the activities they undertake, the actions they
perform, and the items (e.g., movies, restaurants, blogs, etc.) they create and
interact with. There are two key challenges facing these tasks: how to organize and
model social media content, which is often unstructured in its raw form, in order to
employ structured analytics on it; and how to employ analytics algorithms to
capture both explicit link-based relationships and implicit behavior-based
relationships.

Communities are a property of many networks in which a particular network may

have multiple communities such that nodes inside a community are densely
connected. Community detection methods can be broadly categorized into two
types; Agglomerative Methods and Divisive Methods. In Agglomerative
methods, edges are added one by one to a graph which only contains nodes. Edges
are added from the stronger edge to the weaker edge. Divisive methods follow the
opposite of agglomerative methods. In there, edges are removed one by one from a
complete [Link] can be any number of communities in a given network and
they can be of varying sizes. These characteristics make the detection procedure of
communities very hard. However, there are many different techniques proposed in
the domain of community detection.

Online social networks such as Weibo, Twitter, and Facebook provide valuable
platforms for information diffusion among their users. During this process, social
influence occurs when a person’s opinions, emotions, or behaviors are affected by
other people. Thus, changes occur in an individual’s attitudes, thoughts, feelings, or
behaviors as a result of interaction with other people or groups. Social influence
analysis (SIA) is becoming an important research field in social networks. SIA
mainly studies how to model the influence diffusion process in networks, and how
to propose an efficient method to identify a group of target nodes in a network.

NetworkX API in Python

• Import network as nx

• Import [Link]

SMA Lab/VIII 23
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
• G = [Link]()
• G.add_nodes_from([a,b,c])

• [Link]()
• G.add_edge(a,b)
• G.add_edge(a,c)
• [Link]()
• [Link](G)
• [Link]()

Degree Centrality
•To display the degree of each node in graph:
[Link](G)
• For computing degree centrality of each node:
nx.degree_centrality(G)

Closeness Centrality
Find the shortest path from the given node to other node
nx.shortest_path(G,’7’,’9’)

Betweenness centrality
Measures how important a node is to the shortest path through the network
nx.betweenness_centrality(G)

Eigenvector centrality
• Measures a node’s importance
• Links from important nodes
• Node’s influence nx.eigenvector_centrality(G)
CONCLUSION: Hence, we have successfully studied and demonstrated to
Develop Structure based social media analytics model for any business.

SMA Lab/VIII 24
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 7
AIM:To Develop a dashboard and reporting tool based on real time social media
data.

THEORY:
What is a social media dashboard?
A social media dashboard monitors your social media performance metrics like
engagement, subscriber or follower count, and audience insights. Social media
dashboards bring together metrics from platforms like Facebook, Twitter, and
YouTube to display your social media marketing performance in a single view.
When you track your metrics on a social media dashboard, you have quick access
to insights that will help you make smart, data-driven marketing decisions.
Why should I use a social media dashboard?
A social media monitoring dashboard displays all your metrics in a single view.
Use your social media metrics to shape your marketing strategy, engage with your
audience, increase your conversion rates, and generate revenue. Social media
dashboards allow you to gain insight with a single glance and share your
performance with your team so you can stay on top of your social media strategies.
What should be on a social media dashboard?
The top social media metrics for data-driven marketers include:
 Followers
 Content Engagement
 Reach
 Impressions
 Likes, Comments, and Shares
 Post Clicks
 Average Video Watch Time
 Retweets and mentions
A social media dashboard is a platform that allows you to view all of your social
media activity in one place. This includes scheduling and creating posts, tracking
analytics, and interacting with your [Link] best social media dashboards
will also allow you to do things like track trending content, manage ad campaigns,
and analyze results across platforms. Not only does this make social media
marketing more efficient, but it also allows you to get a better understanding of
your overall social media performance — something that is nearly impossible to do
while toggling back-and-forth between native social media business profile
solutions.
Want to see how a social media dashboard works in action? The video below
shows an overview of the Hootsuite dashboard.

SMA Lab/VIII 25
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

fig7.1Social media performance

fig 7.2 Instagram Dashboard

CONCLUSION:Hence, we have successfully studied to Develop a dashboard and

reporting tool based on real time social media data.

SMA Lab/VIII 26
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 8

AIM: To Design the creative content for promotion of your business on social
media using graphics tools such as Adobe Photoshop or Canva

THEORY:
Social media marketing can help increase brand awareness, brand
recognition, and sales while improving your relationships with customers. A
quality social media content plan can help you earn more followers and reach more
people. When used correctly, social media marketing can help take your brand to
the next level by reaching customers where they spend their time online.
What is a social media content plan?
Creating good social media content requires a plan. A social media content plan is part of
your overall marketing strategy; it helps you effectively plan the types of content you post
on different social media platforms depending on your audience. A content plan should
consist of the use of multiple types of content, including videos, blogs, eBooks, videos,
and content developed just for stories.
Steps to create a social media content plan:
1. Learn about your audience
2. Set goals
3. Perform competitive analysis
4. Gather content
5. Develop a content creation plan
6. Create a calendar
7. Evaluate content
Types of social media content to post:
1. Written posts, blogs, articles, guides, and more
2. Electronic books (eBooks)
3. Links to external content
4. Images
5. Video Stories
6. Testimonials and reviews
7. Announcements

SMA Lab/VIII 27
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

CONCLUSION: Thus we have successfully Design the creative content for

promotion of your business on social media using graphics tools such as Adobe
Photoshop or Canva

SMA Lab/VIII 28
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 9

AIM: To analyze competitor activities using social media data.

THEORY:
A competitive analysis is an analysis of your competition to find out
what their strengths and weaknesses are, and how those strengths and weaknesses compare
to your own.

It is a process of benchmarking your own results against the heavy-hitters in your industry,
so you can identify opportunities for growth as well as strategies that aren’t performing as
well as they should.

A social media competitive analysis, specifically, will help you:

 Identify who your competitors are on social media

 Know which social platforms they’re on
 Know how they’re using those platforms
 Understand how well their social strategy is working
 Benchmark your social results against the competition
 Identify social threats to your business
 Find gaps in your own social media marketing strategy
How to do a competitive analysis on social media:

Step 1. Determine who your competitors are

Step 2. Gather intel

Step 3. Do a SWOT analysis

 S – Strengths
 W – Weaknesses
 O– Opportunities
 T – Threats
Step 4. Incorporate the latest data with social media monitoring

Twitter sentiment analysis using Python:

1. Scrape Twitter data (For ChatGPT4 Tweets).

2. the tweets can be downloaded in JSON format
3. use Python for sentiment analysis and Visualization.

SMA Lab/VIII 29
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
CONCLUSION: Hence, we have successfully studied to analyse competitor
activities using social media data.

SMA Lab/VIII 30
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering

Experiment No. 10
AIM: To develop social media text analytics models for improving existing
product/ service by analyzing customer ‘s reviews/comments.

THEORY:
Text mining is the process of examining large collections of text
and converting the unstructured text data into structured data for further analysis
like visualization and model building. In this article, We will utilize the power of
text mining to do an in-depth analysis of customer reviews on an e-commerce
clothing site.
Customer reviews are a great source of “Voice of customer” and could offer
tremendous insights into what customers like and dislike about a product or
service. For the e-commerce business, customer reviews are very critical, since
existing reviews heavily influence buying decision of new customers in the absence
of the actual look and feel of the product to be purchased.
How to use text analytics to improve CX
Step 1: create dashboards to see the data that matters the most
Step 2: analyze data to avoid losing customers
Step 3: get insights on what your customer thinks about specific areas
Step 4: discover hidden trends the moment they arise
Step 5: understand what your customers think about support staff
A strong customer analytics process helps you understand who your customers are,
how they behave, and how satisfied they are with your company or product
experience. Customer analytics are as important as financial reports in gauging the
health of your [Link] analytics dashboards and reports can track team
performance, identify bottlenecks before a process breaks, and measure customer
satisfaction (CSAT) on an ongoing basis. This data can help you build efficiencies,
understand customer needs and behaviors, and resolve problems faster — or
eliminate them altogether.
What is review analysis?
Review analysis is the process of transforming unstructured review data to
structured data that can be used to guide decision-making.
A few of the primary uses include:
 Product feature ideas: scanning product reviews for sentiment on desired
features
 Roadmap prioritization: determining what the dev team should focus on
first

 Bug tracking: scanning new reviews in real-time

 Customer care ratings: determining what customer service departments are
delivering good service.
SMA Lab/VIII 31
 Shivajirao S Jondhale College of Engineering, Dombivli (E)
Department of Computer Engineering
Product reviews are one of the most comprehensive and useful sources of insider
info available, anywhere. These often have gold nuggets that can guide
development, troubleshoot new initiatives, and improve customer experience. They
provide a helpful benchmark to compare your offerings to the competition,
showing both your strong points and areas in which, you need to close the gap.
Think free customer research, there before you’ve even thought to ask.

CONCLUSION: Hence, we have successfully developed social media text

analytics models for improving existing product/ service

SMA Lab/VIII 32