DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

Subject Name: DATA SCIENCE AND DIGITAL MARKETING SYSTEM

Subject Code:U20CST718
Prepared By:
Mr.S.KUMARAKRISHNAN, Asst.Prof/ CSE
Mrs.P.BHAVANI, Asst.Prof / CSE
Mrs.R.DEEPA, Asst.Prof / CSE

Verified by: Approved by:

SYLLABUS:
INTRODUCTION OF DATA SCIENCE - SCOPE OF DATA SCIENCE – DATA SCIENCE WITH OTHER FIELDS –
RELATIONSHIP BETWEEN DATA SCIENCE AND INFORMATION SCIENCE. DATA – DATA TYPES – DATA
COLLECTION – DATA PRE-PROCESSING. INTRODUCTION TO THE LATEST SOCIAL MEDIA LANDSCAPE
AND IMPORTANCE - INTRODUCING SOCIAL GRAPH - DELVING INTO SOCIAL DATA - UNDERSTANDING
THE PROCESS - WORKING ENVIRONMENT - COLLECTING THE DATA - ANALYZING THE DATA -
VISUALIZING THE DATA - GETTING STARTED WITH THE TOOLSET.

UNIT I INTRODUCTION TO DATA SCIENCE AND SOCIAL MEDIA (9 Hrs)

INTRODUCTION OF DATA SCIENCE
 Data Science is a combination of multiple disciplines that uses statistics, data analysis, and machine
learning to analyze data and to extract knowledge and insights from it.

What is Data Science?

 Data Science is about data gathering, analysis and decision-making.
 Data Science is about finding patterns in data, through analysis, and make future predictions.
By using Data Science, companies are able to make:
 Better decisions (should we choose A or B)
 Predictive analysis (what will happen next?)
 Pattern discoveries (find pattern, or maybe hidden information in the data)

Where is Data Science Needed?

 Data Science is used in many industries in the world today, e.g. banking, consultancy, healthcare, and
manufacturing.

Examples of where Data Science is needed:

 For route planning: To discover the best routes to ship
 To foresee delays for flight/ship/train etc. (through predictive analysis)
 To create promotional offers
 To find the best suited time to deliver goods
 To forecast the next years revenue for a company

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  To analyze health benefit of training
 To predict who will win elections

Data Science can be applied in nearly every part of a business where data is available. Examples are:
 Consumer goods
 Stock markets
 Industry
 Politics
 Logistic companies
 E-commerce

How Does a Data Scientist Work?

A Data Scientist requires expertise in several backgrounds:
 Machine Learning
 Statistics
 Programming (Python or R)
 Mathematics
 Databases

A Data Scientist must find patterns within the data. Before he/she can find the patterns, he/she must organize the
data in a standard format.

Here is how a Data Scientist works:

 Ask the right questions - To understand the business problem.
 Explore and collect data - From database, web logs, customer feedback, etc.
 Extract the data - Transform the data to a standardized format.
 Clean the data - Remove erroneous values from the data.
 Find and replace missing values - Check for missing values and replace them with a suitable value (e.g.
an average value).
 Normalize data - Scale the values in a practical range (e.g. 140 cm is smaller than 1,8 m. However, the
number 140 is larger than 1,8. - so scaling is important).
 Analyze data, find patterns and make future predictions.
 Represent the result - Present the result with useful insights in a way the "company" can understand.

Problem Statement: No work start without motivation, Data science is no exception though. It’s really
important to declare or formulate your problem statement very clearly and precisely. Your whole model and it’s
working depend on your statement. Many scientist considers this as the main and much important step of Date
Science. So make sure what’s your problem statement and how well can it add value to business or any other
organization.

Data Collection: After defining the problem statement, the next obvious step is to go in search of data that you
might require for your model. You must do good research, find all that you need. Data can be in any form i.e
unstructured or structured. It might be in various forms like videos, spreadsheets, coded forms, etc. You must
collect all these kinds of sources.

Data Cleaning: As you have formulated your motive and also you did collect your data, the next step to do is
cleaning. Yes, it is! Data cleaning is the most favorite thing for data scientists to do. Data cleaning is all about the
removal of missing, redundant, unnecessary and duplicate data from your collection. There are various tools to
do so with the help of programming in either R or Python. It’s totally on you to choose one of them. Various
scientist have their opinion on which to choose. When it comes to the statistical part, R is preferred over Python,

SMVEC – COMPUTER SCIENCE AND ENGINEERING

as it has the privilege of more than 12,000 packages. While python is used as it is fast, easily accessible and we
can perform the same things as we can in R with the help of various packages.

Data Analysis and Exploration: It’s one of the prime things in data science to do and time to get inner Holmes
out. It’s about analyzing the structure of data, finding hidden patterns in them, studying behaviors, visualizing the
effects of one variable over others and then concluding. We can explore the data with the help of various graphs
formed with the help of libraries using any programming language. In R, GGplot is one of the most famous
models while Matplotlib in Python.

Data Modelling: Once you are done with your study that you have formed from data visualization, you must
start building a hypothesis model such that it may yield you a good prediction in future. Here, you must choose a
good algorithm that best fit to your model. There different kinds of algorithms from regression to classification,
SVM( Support vector machines), Clustering, etc. Your model can be of a Machine Learning algorithm. You train
your model with the train data and then test it with test data. There are various methods to do so. One of them is
the K-fold method where you split your whole data into two parts, One is Train and the other is test data. On
these bases, you train your model.

Optimization and Deployment: You followed each and every step and hence build a model that you feel is the
best fit. But how can you decide how well your model is performing? This where optimization comes. You test
your data and find how well it is performing by checking its accuracy. In short, you check the efficiency of the
data model and thus try to optimize it for better accurate prediction. Deployment deals with the launch of your
model and let the people outside there to benefit from that. You can also obtain feedback from organizations and
people to know their need and then to work more on your model.

SCOPE OF DATA SCIENCE(JAN 2024)(2marks)

 Coming to career scope in Data Science, it is vast. According to analysts, the country would have over 11
million employment opportunities by 2026. Indeed, the data science field has seen a 46% surge in
recruiting since 2019.
 Despite this, roughly 93,000 Data Science positions were open in India by the end of August 2020.
Hence, there is no doubt in the future scope of Data Science. Moreover, with Data Science knowledge,
you can get various job opportunities to excel in your career. Other than Data Scientist’s role, there are
many job roles available in this career such as:

 Data Analyst: Data analysts are responsible for analyzing data utilizing data analysis tools and assisting
their teams in developing insights and business plans.

 Data Engineer: Data Engineer’s purpose is to offer an orderly, uniform data flow that enables data-
driven models like machine learning models and data analysis.

 Machine Learning Engineer: Working as a machine learning engineer, you’ll be in charge of

developing models and algorithms that allow machines to function automatically.

 Business Analyst: Using data analysis, business analysts assist companies in enhancing processes, goods,
services, and software.

 Data Architect: A data architect is a specialist who develops the business’s data strategy, which includes
data quality standards, data movement within the organization, and data security.

 Data Administrator: A database administrator (DBA) is a person who is in charge of the database
management system’s administration, management, coordination, and operation.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  Data Manager: A Data Manager assesses the company’s or research organization’s data demands and
employs coding abilities to keep databases secure.

 Marketing Analyst: A marketing analyst does research to determine what customers need and desire, as
well as assess the efficiency of a company’s marketing and commercial strategy.

Data Science is rather a crude term. It consists of many fields of study. With the expansion of the Data Science
field, the roles in Data Science have also expanded. This has resulted in the growth of operations in the life cycle
of Data Science, and we are near to exploring the world of Data Science with a more creative vision. Hence,
learn Data Science to make a blazing career in Data Science.

HOW DOES DATA SCIENCE RELATE TO OTHER FIELDS?

Data Science and Statistics
Statistician and data visualizer Nathan Yau of Flowing Data suggests that data scientists should have at least
three basic skills:
1. A strong knowledge of basic statistics and machine learning – or at least enough to avoid misinterpreting
correlation for causation or extrapolating too much from a small sample size.
2. The computer science skills to take an unruly dataset and use a programming language (like R or Python) to
make it easy to analyze.
3. The ability to visualize and express their data and analysis in a way that is meaningful to somebody less
conversant in data.

Data Science and Computer Science

Computer scientists have developed numerous techniques and methods, such as
(1) database (DB) systems that can handle the increasing volume of data in both structured and unstructured
formats, expediting data analysis;
(2) visualization techniques that help people
make sense of data; and
(3) algorithms that make it possible to compute complex and heterogeneous data in less time.

Data Science and Engineering

Broadly speaking, engineering in various fields (chemical, civil, computer, mechanical, etc.) has created demand
for data scientists and data science methods. Engineers constantly need data to solve problems. Data scientists
have been called upon to develop methods and techniques to meet these needs. Likewise, engineers have assisted
data scientists. Data science has benefitted from new software and hardware developed via engineering, such as
the CPU (central processing unit) and GPU (graphic processing unit) that substantially reduce computing time.
Take the example of jobs in civil engineering. The trend has drastically changed in the construction industry due
to use of technology in the last few decades.

Data Science and Business Analytics

In general, we can say that the main goal of “doing business” is turning a profit – even with limited resources –
through efficient and sustainable manufacturing methods, and effective service models, etc. This demands
decision-making based on objective evaluation, for which data analysis is essential.
Business analytics (BA) refers to the skills, technologies, and practices for continuous iterative exploration and
investigation of past and current business performance to gain insight and be strategic. BA focuses on developing
new perspectives and making sense of performance based on data and statistics. And that is where data science
comes in. To fulfill the requirements of BA, data scientists are needed for statistical analysis, including
explanatory and predictive modeling and fact-based management, to help drive successful decision-making.
There are four types of analytics, each of which holds opportunities for data scientists in business analytics:
1. Decision analytics: supports decision-making with visual analytics that reflect reasoning.
2. Descriptive analytics: provides insight from historical data with reporting, score cards, clustering, etc.
3. Predictive analytics: employs predictive modeling using statistical and machine learning techniques.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

4. Prescriptive analytics: recommends decisions using optimization, simulation, etc.

Data Science, Social Science, and Computational Social Science

Computational social science raises inevitable questions about the politics and ethics often embedded in data
science research, particularly when it is based on sociopolitical problems with real-life applications that have far-
reaching consequences. Government policies, people’s mandates in elections, and hiring strategies in the private
sector, are prime examples of such
applications.

THE RELATIONSHIP BETWEEN DATA SCIENCE AND INFORMATION SCIENCE

Data is everywhere. Humans and machines are constantly creating new data. Just as natural science focuses on
understanding the characteristics and laws that govern natural phenomena, data scientists are interested in
investigating the characteristics of data – looking for patterns that reveal how people and society can benefit from
data. That
perspective often misses the processes and people behind the data, as most researchers and professionals see data
from the system side and subsequently focus on quantifying phenomena; they lack an understanding of the users’
perspective. Information scientists, who look at data in the context they are generated and used, can play an
important role that bridges the gap between quantitative analysis and an examination of data that tells a story.

Information vs. Data

The Data, Information, Knowledge, and Wisdom (DIKW) model differentiates the meaning of each concept and
suggests a hierarchical system among them. Although various authors and scholars offer several interpretations
of this model, the model defines data as
(1) fact,
(2) signal, and
(3) symbol. Here, information is differentiated from data in that it is “useful.”
Unlike conceptions of data in other disciplines, information science demands and presumes a thorough
understanding of information, considering different contexts and circumstances related to the data that is created,
generated, and shared, mostly by human beings.

Users in Information Science

Studies in information science have focused on the human side of data and information, in addition to the system
perspective. While the system perspective typically supports users’ ability to observe, analyze, and interpret the
data, the former allows them to make the data into useful information for their purposes. Different users may not
agree on a piece of information’s relevancy depending on various factors that affect judgment, such as
“usefulness.” Usefulness is a criterion that determines how useful is the interaction between the user and the
information object (data) in accomplishing the task or goal of the user.
For example, a general user who wants to figure out if drinking coffee is injurious to health may find information
in the search engine result pages (SERP) to be useful, whereas a dietitian who needs to decide if it is OK to
recommend a patient to consume coffee may find the same result in SERP worthless. Therefore,
operationalization of the criterion of usefulness will be specific to the user’s task. Scholars in information science
tend to combine the user side and the system side to understand how and why data is generated and the
information they convey, given a context.

Data Science in Information Schools (iSchools)

There are several advantages to studying data science in information schools, or iSchools. Data science provides
students a more nuanced understanding of individual, community, and society-wide phenomena. Students may,
for instance, apply data collected from a particular community to enhance that locale’s wellbeing through policy
change and/or urban planning. Essentially, an iSchool curriculum helps students acquire diverse perspectives on
data and information. This becomes an advantage as students transition into fullfledged data scientists with a
grasp on the big (data) picture. In addition to all the required data science skills and knowledge (including

SMVEC – COMPUTER SCIENCE AND ENGINEERING

understanding computer science, statistics, machine learning, etc.), the focus on the human factor gives students
distinct opportunities. An iSchool curriculum also provides a depth of contextual understanding of information.
Studying data science in an iSchool offers unique chances to understand data in contexts including
communications, information studies, library science, and media research. The difference between studying data
science in an iSchool, as opposed to within a computer science or statistics program, is that the former tends to
focus on analyzing data and extracting insightful information grounded in context.

DATA TYPES
DATA
 “Data is a precious thing and will last longer than the systems themselves.”
 There are two types of data: Qualitative and Quantitative data, which are further classified into four types
of data: nominal, ordinal, discrete, and Continuous.

Now business runs on data, most of the companies use data for their insights to create and launch campaigns,
design strategies, launch products, and services or try out different things. According to a report, today, at least
2.5 quintillion bytes of data are produced per day.

Types of Data
Qualitative or Categorical Data
 Qualitative or Categorical Data is data that can’t be measured or counted in the form of numbers. These
types of data are sorted by category, not by number. That’s why it is also known as Categorical Data.
 These data consist of audio, images, symbols, or text. The gender of a person, i.e., male, female, or others,
is qualitative data.
 Qualitative data tells about the perception of people. This data helps market researchers understand the
customers’ tastes and then design their ideas and strategies accordingly.

The other examples of qualitative data are :

 What language do you speak
 Favorite holiday destination
 Opinion on something (agree, disagree, or neutral)
 Colors

The Qualitative data are further classified into two parts :

Nominal Data
 Nominal Data is used to label variables without any order or quantitative value. The colour of hair can be
considered nominal data, as one colour can’t be compared with another colour.
 The name “nominal” comes from the Latin name “nomen,” which means “name.” With the help of
nominal data, we can’t do any numerical tasks or can’t give any order to sort the data. These data don’t
have any meaningful order; their values are distributed to distinct categories.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Examples of Nominal Data :
 Colour of hair (Blonde, red, Brown, Black, etc.)
 Marital status (Single, Widowed, Married)
 Nationality (Indian, German, American)
 Gender (Male, Female, Others)
 Eye Color (Black, Brown, etc.)

Ordinal Data
 Ordinal data have natural ordering where a number is present in some kind of order by their position on
the scale. These data are used for observation like customer satisfaction, happiness, etc., but we can’t do
any arithmetical tasks on them.
 The ordinal data is qualitative data for which their values have some kind of relative position. These kinds
of data can be considered as “in-between” the qualitative data and quantitative data. The ordinal data only
shows the sequences and cannot use for statistical analysis. Compared to the nominal data, ordinal data
have some kind of order that is not present in nominal data.

Examples of Ordinal Data :

 When companies ask for feedback, experience, or satisfaction on a scale of 1 to 10
 Letter grades in the exam (A, B, C, D, etc.)
 Ranking of peoples in a competition (First, Second, Third, etc.)
 Economic Status (High, Medium, and Low)
 Education Level (Higher, Secondary, Primary)

Difference between Nominal and Ordinal Data

Nominal Data Ordinal Data
Nominal data can’t be quantified, neither they Ordinal data gives some kind of sequential order by
have any intrinsic ordering their position on the scale
Nominal data is qualitative data or categorical Ordinal data is said to be “in-between” qualitative
data data and quantitative data
They don’t provide any quantitative value, They provide sequence and can assign numbers to
neither we can perform any arithmetical ordinal data but cannot perform the arithmetical
operation operation
Nominal data cannot be used to compare with one Ordinal data can help to compare one item with
another another by ranking or ordering
Examples: Eye colour, housing style, gender, Examples: Economic status, customer satisfaction,
hair colour, religion, marital status, ethnicity, etc education level, letter grades, etc

Quantitative Data
 Quantitative data can be expressed in numerical values, which makes it countable and includes statistical
data analysis. These kinds of data are also known as Numerical data. It answers the questions like, “how
much,” “how many,” and “how often.” For example, the price of a phone, the computer’s ram, the height
or weight of a person, etc., falls under the quantitative data.
 Quantitative data can be used for statistical manipulation and these data can be represented on a wide
variety of graphs and charts such as bar graphs, histograms, scatter plots, boxplot, pie charts, line graphs,
etc.

Examples of Quantitative Data :

 Height or weight of a person or object

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  Room Temperature
 Scores and Marks (Ex: 59, 80, 60, etc.)
 Time

The Quantitative data are further classified into two parts :

Discrete Data
 The term discrete means distinct or separate. The discrete data contain the values that fall under integers
or whole numbers. The total number of students in a class is an example of discrete data. These data can’t
be broken into decimal or fraction values.
 The discrete data are countable and have finite values; their subdivision is not possible. These data are
represented mainly by a bar graph, number line, or frequency table.

Examples of Discrete Data :

 Total numbers of students present in a class
 Cost of a cell phone
 Numbers of employees in a company
 The total number of players who participated in a competition
 Days in a week

Continuous Data
Continuous data are in the form of fractional numbers. It can be the version of an android phone, the height of a
person, the length of an object, etc. Continuous data represents information that can be divided into smaller
levels. The continuous variable can take any value within a range.

The key difference between discrete and continuous data is that discrete data contains the integer or whole
number. Still, continuous data stores the fractional numbers to record different types of data such as temperature,
height, width, time, speed, etc.

Examples of Continuous Data :

Height of a person
Speed of a vehicle
“Time-taken” to finish the work
Wi-Fi Frequency
Market share price

Difference between Discrete and Continuous Data

Discrete Data Continuous Data
Discrete data are countable and finite; they are Continuous data are measurable; they are in the form
whole numbers or integers of fraction or decimal
Discrete data are represented mainly by bar Continuous data are represented in the form of a
graphs histogram
The values cannot be divided into subdivisions The values can be divided into subdivisions into
into smaller pieces smaller pieces
Continuous data are in the form of a continuous
Discrete data have spaces between the values
sequence
Examples: Total students in a class, number of Example: Temperature of room, the weight of a
days in a week, size of a shoe, etc person, length of an object, etc

DATA COLLECTION
What is data collection?

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  Data collection is the process of gathering data for use in business decision-making, strategic planning,
research and other purposes. It's a crucial part of data analytics applications and research projects:
 Effective data collection provides the information that's needed to answer questions, analyze business
performance or other outcomes, and predict future trends, actions and scenarios.
 In businesses, data collection happens on multiple levels. IT systems regularly collect data on customers,
employees, sales and other aspects of business operations when transactions are processed and data is
entered.
 Companies also conduct surveys and track social media to get feedback from customers. Data scientists,
other analysts and business users then collect relevant data to analyze from internal systems, plus external
data sources if needed.
 The latter task is the first step in data preparation, which involves gathering data and preparing it for use
in business intelligence (BI) and analytics applications.
 For research in science, medicine, higher education and other fields, data collection is often a more
specialized process, in which researchers create and implement measures to collect specific sets of data.
In both the business and research contexts, though, the collected data must be accurate to ensure that
analytics findings and research results are valid.

What are different methods of data collection?

 Data can be collected from one or more sources as needed to provide the information that's being sought.
For example, to analyze sales and the effectiveness of its marketing campaigns, a retailer might collect
customer data from transaction records, website visits, mobile applications, its loyalty program and an
online survey.
 The methods used to collect data vary based on the type of application. Some involve the use of
technology, while others are manual procedures. The following are some common data collection
methods:
 automated data collection functions built into business applications, websites and mobile apps;
 sensors that collect operational data from industrial equipment, vehicles and other machinery;
 collection of data from information services providers and other external data sources;
 tracking social media, discussion forums, reviews sites, blogs and other online channels;
 surveys, questionnaires and forms, done online, in person or by phone, email or regular mail;
 focus groups and one-on-one interviews; and
 direct observation of participants in a research study.

What are common challenges in data collection?

Some of the challenges often faced when collecting data include the following:

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Data quality issues.
 Raw data typically includes errors, inconsistencies and other issues. Ideally, data collection measures are
designed to avoid or minimize such problems. As a result, collected data usually needs to be put through
data profiling to identify issues and data cleansing to fix them.
 Finding relevant data. With a wide range of systems to navigate, gathering data to analyze can be a
complicated task for data scientists and other users in an organization. The use of data curation techniques
helps make it easier to find and access data. For example, that might include creating a data catalog and
searchable indexes.
 Deciding what data to collect. This is a fundamental issue both for upfront collection of raw data and
when users gather data for analytics applications. Collecting data that isn't needed adds time, cost and
complexity to the process. But leaving out useful data can limit a data set's business value and affect
analytics results.
 Dealing with big data. Big data environments typically include a combination of structured, unstructured
and semi-structured data, in large volumes. That makes the initial data collection and processing stages
more complex. In addition, data scientists often need to filter sets of raw data stored in a data lake for
specific analytics applications.
 Low response and other research issues. In research studies, a lack of responses or willing participants
raises questions about the validity of the data that's collected. Other research challenges include training
people to collect the data and creating sufficient quality assurance procedures to ensure that the data is
accurate.

What are the key steps in the data collection process?

Well-designed data collection processes include the following steps:
 Identify a business or research issue that needs to be addressed and set goals for the project.
 Gather data requirements to answer the business question or deliver the research information.
 Identify the data sets that can provide the desired information.
 Set a plan for collecting the data, including the collection methods that will be used.
 Collect the available data and begin working to prepare it for analysis.

DATA PRE-PROCESSING
What is data preprocessing?
 Data preprocessing, a component of data preparation, describes any type of processing performed on raw
data to prepare it for another data processing procedure. It has traditionally been an important preliminary
step for the data mining process. More recently, data preprocessing techniques have been adapted for
training machine learning models and AI models and for running inferences against them.
 Data preprocessing transforms the data into a format that is more easily and effectively processed in data
mining, machine learning and other data science tasks. The techniques are generally used at the earliest
stages of the machine learning and AI development pipeline to ensure accurate results.

There are several different tools and methods used for preprocessing data, including the following:
 sampling, which selects a representative subset from a large population of data;
 transformation, which manipulates raw data to produce a single input;
 denoising, which removes noise from data;
 imputation, which synthesizes statistically relevant data for missing values;
 normalization, which organizes data for more efficient access; and
 feature extraction, which pulls out a relevant feature subset that is significant in a particular context.
These tools and methods can be used on a variety of data sources, including data stored in files or databases and
streaming data.

Why is data preprocessing important?(JAN 2024)(2MARKS)

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  Virtually any type of data analysis, data science or AI development requires some type of data
preprocessing to provide reliable, precise and robust results for enterprise applications.
 Real-world data is messy and is often created, processed and stored by a variety of humans, business
processes and applications. As a result, a data set may be missing individual fields, contain manual input
errors, or have duplicate data or different names to describe the same thing. Humans can often identify
and rectify these problems in the data they use in the line of business, but data used to train machine
learning or deep learning algorithms needs to be automatically preprocessed.
 Machine learning and deep learning algorithms work best when data is presented in a format that
highlights the relevant aspects required to solve a problem.
 Feature engineering practices that involve data wrangling, data transformation, data reduction, feature
selection and feature scaling help restructure raw data into a form suited for particular types of
algorithms. This can significantly reduce the processing power and time required to train a new machine
learning or AI algorithm or run an inference against it.

What are the key steps in data preprocessing?

The steps used in data preprocessing include the following:
1. Data profiling. Data profiling is the process of examining, analyzing and reviewing data to collect statistics
about its quality. It starts with a survey of existing data and its characteristics. Data scientists identify data sets
that are pertinent to the problem at hand, inventory its significant attributes, and form a hypothesis of features
that might be relevant for the proposed analytics or machine learning task. They also relate data sources to the
relevant business concepts and consider which preprocessing libraries could be used.
2. Data cleansing. The aim here is to find the easiest way to rectify quality issues, such as eliminating bad data,
filling in missing data or otherwise ensuring the raw data is suitable for feature engineering.
3. Data reduction. Raw data sets often include redundant data that arise from characterizing phenomena in
different ways or data that is not relevant to a particular ML, AI or analytics task. Data reduction uses techniques
like principal component analysis to transform the raw data into a simpler form suitable for particular use cases.
4. Data transformation. Here, data scientists think about how different aspects of the data need to be organized
to make the most sense for the goal. This could include things like structuring unstructured data, combining
salient variables when it makes sense or identifying important ranges to focus on.
5. Data enrichment. In this step, data scientists apply the various feature engineering libraries to the data to
effect the desired transformations. The result should be a data set organized to achieve the optimal balance
between the training time for a new model and the required compute.
6. Data validation. At this stage, the data is split into two sets. The first set is used to train a machine learning or
deep learning model. The second set is the testing data that is used to gauge the accuracy and robustness of the
resulting model. This second step helps identify any problems in the hypothesis used in the cleaning and feature
engineering of the data. If the data scientists are satisfied with the results, they can push the preprocessing task to
a data engineer who figures out how to scale it for production. If not, the data scientists can go back and make
changes to the way they implemented the data cleansing and feature engineering steps.

Data preprocessing techniques

SMVEC – COMPUTER SCIENCE AND ENGINEERING

There are two main categories of preprocessing -- data cleansing and feature engineering. Each includes a variety
of techniques, as detailed below.

Data cleansing
Techniques for cleaning up messy data include the following:
 Identify and sort out missing data. There are a variety of reasons a data set might be missing individual
fields of data. Data scientists need to decide whether it is better to discard records with missing fields,
ignore them or fill them in with a probable value. For example, in an IoT application that records
temperature, adding in a missing average temperature between the previous and subsequent record might
be a safe fix.
 Reduce noisy data. Real-world data is often noisy, which can distort an analytic or AI model. For
example, a temperature sensor that consistently reported a temperature of 75 degrees Fahrenheit might
erroneously report a temperature as 250 degrees. A variety of statistical approaches can be used to reduce
the noise, including binning, regression and clustering.
 Identify and remove duplicates. When two records seem to repeat, an algorithm needs to determine if
the same measurement was recorded twice, or the records represent different events. In some cases, there
may be slight differences in a record because one field was recorded incorrectly. In other cases, records
that seem to be duplicates might indeed be different, as in a father and son with the same name who are
living in the same house but should be represented as separate individuals. Techniques for identifying and
removing or joining duplicates can help to automatically address these types of problems.

Feature engineering
Feature engineering, as noted, involves techniques used by data scientists to organize the data in ways that make
it more efficient to train data models and run inferences against them. These techniques include the following:

 Feature scaling or normalization. Often, multiple variables change over different scales, or one will
change linearly while another will change exponentially. For example, salary might be measured in
thousands of dollars, while age is represented in double digits. Scaling helps to transform the data in a
way that makes it easier for algorithms to tease apart a meaningful relationship between variables.
 Data reduction. Data scientists often need to combine a variety of data sources to create a new AI or
analytics model. Some of the variables may not be correlated with a given outcome and can be safely
discarded. Other variables might be relevant, but only in terms of relationship -- such as the ratio of debt
to credit in the case of a model predicting the likelihood of a loan repayment; they may be combined into
a single variable. Techniques like principal component analysis play a key role in reducing the number of
dimensions in the training data set into a more efficient representation.
 Discretization. It's often useful to lump raw numbers into discrete intervals. For example, income might
be broken into five ranges that are representative of people who typically apply for a given type of loan.
This can reduce the overhead of training a model or running inferences against it.
 Feature encoding. Another aspect of feature engineering involves organizing unstructured data into a
structured format. Unstructured data formats can include text, audio and video. For example, the process
of developing natural language processing algorithms typically starts by using data transformation
algorithms like Word2vec to translate words into numerical vectors.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

How is data preprocessing used?
 Data preprocessing plays a key role in earlier stages of machine learning and AI application development,
as noted earlier. In an AI context, data preprocessing is used to improve the way data is cleansed,
transformed and structured to improve the accuracy of a new model, while reducing the amount of
compute required.
 A good data preprocessing pipeline can create reusable components that make it easier to test out various
ideas for streamlining business processes or improving customer satisfaction. For example, preprocessing
can improve the way data is organized for a recommendation engine by improving the age ranges used for
categorizing customers.
 Preprocessing can also simplify the work of creating and modifying data for more accurate and targeted
business intelligence insights. For example, customers of different sizes, categories or regions may exhibit
different behaviors across regions. Preprocessing the data into the appropriate forms could help BI teams
weave these insights into BI dashboards.
 In a customer relationship management (CRM) context, data preprocessing is a component of web
mining. Web usage logs may be preprocessed to extract meaningful sets of data called user transactions,
which consist of groups of URL references. User sessions may be tracked to identify the user, the
websites requested and their order, and the length of time spent on each one. Once these have been pulled
out of the raw data, they yield more useful information that can be applied, for example, to consumer
research, marketing or personalization.

INTRODUCTION TO THE LATEST SOCIAL MEDIA LANDSCAPE AND IMPORTANCE(JAN 2024)(5 MARKS)
Introduction to Social Media, Social media landscape
 Social media are interactive 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:
o Social media are interactive Web 2.0 Internet-based applications.
o 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.
o Users create service-specific profiles for the website or app that are designed and maintained by
the social media organization.
o Social media helps the development of online social networks by connecting a user's profile with
those of other individuals or groups.

Social Media and Business

 Since the turn of the century, social media marketing has become a focal point of the advertising and
marketing campaigns of companies both large and small worldwide. Communicating with existing and
potential customers through social media offers numerous advantages to businesses.
 First, compared to traditional avenues of advertising, social media marketing is much less expensive. The
costs for social media marketing often involve only the creation of advertising content and the
compensation for the employees charged with posting material on the various social media websites.
 Second. Businesses can instantly communicate information to their entire database of current and/or
potential customers. They also have the ability to tailor advertising to certain demographic groups and
then communicate that content only to the targeted customer segment.
 The ease of connection and communication through social media platforms enables companies to much
more deeply and effectively engage with their target market. They can converse with customers at length
and in-depth, obtaining valuable feedback about their company and its products and services, and then use
the feedback obtained to craft future marketing campaigns. Through social media sites, a company can
also provide its customers with easy access to customer service. 24/7.
 Social media makes it possible for companies to "humanize" their company and to much more quickly
and easily build, establish and maintain their brand identity and public image.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Types of Social Media
 Social media may take the form of a variety of tech-enabled activities. These activities include photo
sharing, blogging, social gaming, social networks, video sharing. Business networks: virtual worlds,
reviews and much more. Even governments and politicians utilize social media to engage with
constituents and voters.
 For individuals, social media is used to keep in touch with friends and extended family. Some people will
use various social media applications to network career opportunities find people across the globe with
like-minded interests, and share their thoughts, feelings, insights, and emotions. Those who engage in
these activities are part of a virtual social network.
 For businesses, social media is an indispensable tool. Companies use the platform to find and engage with
customers, drive sales through advertising and promotion, gauge consumer trends, and offer customer
service or support.
 Social media's role in helping businesses is significant. It facilitates communication with customers,
enabling the melding of social interactions on e-commerce sites. Its ability to collect information helps
focus on marketing efforts and market research. It helps in promoting products and services. as it enables
the distribution of targeted, timely, and exclusive sales and coupons to would-be customers. Further,
social media can help in building customer relationships through loyalty programs linked to social media.

Benefits of Social Media

 Social media has changed the way we all interact with each other online. It gives us the ability to
discover what's happening in the world in real-time, to connect with each other and stay in touch with
long-distance friends and in order to have access to endless amounts of information at our fingertips.
In many senses, social media has helped many individuals find common ground with others online
making the world seem more approachable.
 According to a survey by Pew Research Center, the use of social media is correlated with having more
friends and more diverse personal networks, especially within emerging economies. For many
teenagers friendships can start virtually, with 57% of teens meeting a friend online.
 Businesses are also using social media marketing to target their consumers right on their phones and
computers, building a following in order to build a loyal fan base, and create a culture behind their
own brand. Some companies such as Denny's, have created entire personas on Twitter in order to
market to younger consumers using their own language and personas.

The Dangers Posed by Social Media Platforms

 Social media has exploded in popularity, among all types of people, all across the world. In the developed
world and emerging market countries, nearly everyone is a user of at least one social media platform.
However, social media's widespread adoption and use have created significant new threats to things such
as people’s privacy and mental health.
 Recent studies by psychologists have uncovered the facts that people engaging with others through social
media has led to measurable increases in depression, stress/anxiety, suicides (especially among young
people), and problems of low self-esteem.
 In addition to the threats posed to our mental health, the widespread use of social media has also created
and/or amplified threats of a more practical, tangible nature such as stalking, identity theft invasion of
privacy and political and social polarization.
 The very real and substantive potential dangers posed by social media are even the subject of two
recently-released Netflix original movies "The Social Dilemma" and -The Great Hack." The subject
explored in the 2019 documentary, "The Great Hack". is the Cambridge Analytical scandal.
 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.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  It is beneficial to build a presence online that is communicative connects with your customers, shares
your content and highlights your skills through the different platforms of social media.
 The social media landscape is constantly growing, changing and improving. Is your business present and
active in the social media landscape?
 It is an area of marketing that you should definitely start exploring. Being able to engage with your
followers puts you at a huge advantage over your competitors.
 Simply it's the social 'ecosystem" where we can distinguish tools for:
o Publishing (with blog platforms),
o Sharing (videos or music platforms),
o Discussing (like quora and comment platforms),
o Collaborating,
o Messaging (mobile. visual and webmails)
o And networking (with dating and meeting platforms)

INTRODUCING SOCIAL GRAPH

 The social graph is a graph that represents social relations between entities. In short, it is a model or
representation of a social network, where the word graph has been taken from graph theory. The social
graph has been referred to as "the global mapping of everybody and how they're related".
 The term was used as early as 1964, albeit in the context of isoglosses. Leo Apostel uses the term in the
context here in 1978. The concept was originally called sociogram.
 The term was popularized at the Facebook F8 conference on May 24, 2007, when it was used to explain
how the newly introduced Facebook Platform would take advantage of the relationships between
individuals to offer a richer online experience. The definition has been expanded to refer to a social graph
of all Internet users.
 Since explaining the concept of the social graph, Mark Zuckerberg, one of the founders of Facebook, has
often touted Facebook's goal of offering the website's social graph to other websites so that a user's
relationships can be put to use on websites outside Facebook's control.

A drawing of a graph in which each person is represented by a dot called a node and the friendship
relationship is represented by a line called an edge

 A social graph is a diagram that illustrates interconnections among people, groups and organizations in a
social network. The term is also used to describe an individual's social network.
 When portrayed as a map, a social graph appears as a set of network nodes that are connected by lines.
Each node, which may also be referred to as an actor, is actually a data record. The connecting lines used
to map relationships between data records are referred to as edges, ties or interdependencies.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  When a social graph has a small number of nodes, it can easily be mapped on a whiteboard or piece of
paper, using color-coded solid and dotted lines to indicate relationships. When the social graph has a large
number of nodes, however, crisscrossed ties can quickly become tangled, making it difficult for anyone to
get meaningful information out of the diagram. Graph database software such as Apache Giraph makes it
easier to analyze a large, complex social graph database through queries. This is how most social media
sites, including Facebook, use search algorithms to personalize news feeds and target advertising.

Facebook and social graphs

 CEO Mark Zuckerberg is credited with first using the term "social graph" in 2007 to refer to the network
of connections and relationships documented by Facebook members. Although Facebook provides third
parties with limited access to members' social graphs through application programming interfaces (APIs),
the site is often criticized for being a walled garden that constricts social graph portability, as well as the
potential power of social graphs in general, by requiring members to recreate their social graphs manually
in other applications.

DELVING INTO SOCIAL DATA

UNDERSTANDING THE PROCESS

Data Science is all about a systematic process used by Data Scientists to analyze, visualize and model large
amounts of data. A data science process helps data scientists use the tools to find unseen patterns, extract
data, and convert information to actionable insights that can be meaningful to the company. This aids
companies and businesses in making decisions that can help in customer retention and profits. Further, a
data science process helps in discovering hidden patterns of structured and unstructured raw data. The

SMVEC – COMPUTER SCIENCE AND ENGINEERING

process helps in turning a problem into a solution by treating the business problem as a project. So, let us
learn what is data science process is in detail and what are the steps involved in a data science process.
The six steps of the data science process are as follows:
1. Frame the problem
2. Collect the raw data needed for your problem
3. Process the data for analysis
4. Explore the data
5. Perform in-depth analysis
6. Communicate results of the analysis
As the data science process stages help in converting raw data into monetary gains and overall profits, any
data scientist should be well aware of the process and its significance. Now, let us discuss these steps in
detail.
Steps in Data Science Process
A data science process can be more accurately understood through data science online courses and
certifications on data science. But, here is a step-by-step guide to help you get familiar with the process.

Step 1: Framing the Problem

Before solving a problem, the pragmatic thing to do is to know what exactly the problem is. Data questions
must be first translated to actionable business questions. People will more than often give ambiguous
inputs on their issues. And, in this first step, you will have to learn to turn those inputs into actionable
outputs.
A great way to go through this step is to ask questions like:
 Who the customers are?
 How to identify them?
 What is the sale process right now?
 Why are they interested in your products?
 What products they are interested in?
You will need much more context from numbers for them to become insights. At the end of this step, you
must have as much information at hand as possible.
Step 2: Collecting the Raw Data for the Problem
After defining the problem, you will need to collect the requisite data to derive insights and turn the
business problem into a probable solution. The process involves thinking through your data and finding
ways to collect and get the data you need. It can include scanning your internal databases or purchasing
databases from external sources.
Many companies store the sales data they have in customer relationship management (CRM) systems. The
CRM data can be easily analyzed by exporting it to more advanced tools using data pipelines.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

 Step 3: Processing the Data to Analyze
After the first and second steps, when you have all the data you need, you will have to process it before
going further and analyzing it. Data can be messy if it has not been appropriately maintained, leading to
errors that easily corrupt the analysis. These issues can be values set to null when they should be zero or
the exact opposite, missing values, duplicate values, and many more. You will have to go through the data
and check it for problems to get more accurate insights.
The most common errors that you can encounter and should look out for are:
1. Missing values
2. Corrupted values like invalid entries
3. Time zone differences
4. Date range errors like a recorded sale before the sales even started
You will have to also look at the aggregate of all the rows and columns in the file and see if the values you
obtain make sense. If it doesn’t, you will have to remove or replace the data that doesn’t make sense. Once
you have completed the data cleaning process, your data will be ready for an exploratory data analysis
(EDA).
Step 4: Exploring the Data
In this step, you will have to develop ideas that can help identify hidden patterns and insights. You will
have to find more interesting patterns in the data, such as why sales of a particular product or service have
gone up or down. You must analyze or notice this kind of data more thoroughly. This is one of the most
crucial steps in a data science process.
Step 5: Performing In-depth Analysis
This step will test your mathematical, statistical, and technological knowledge. You must use all the data
science tools to crunch the data successfully and discover every insight you can. You might have to
prepare a predictive model that can compare your average customer with those who are underperforming.
You might find several reasons in your analysis, like age or social media activity, as crucial factors in
predicting the consumers of a service or product.
You might find several aspects that affect the customer, like some people may prefer being reached over
the phone rather than social media. These findings can prove helpful as most of the marketing done
nowadays is on social media and only aimed at the youth. How the product is marketed hugely affects
sales, and you will have to target demographics that are not a lost cause after all. Once you are all done
with this step, you can combine the quantitative and qualitative data that you have and move them into
action.
Step 6: Communicating Results of this Analysis
After all these steps, it is vital to convey your insights and findings to the sales head and make them
understand their importance. It will help if you communicate appropriately to solve the problem you have
been given. Proper communication will lead to action. In contrast, improper contact may lead to inaction.
You need to link the data you have collected and your insights with the sales head’s knowledge so that they
can understand it better. You can start by explaining why a product was underperforming and why specific
demographics were not interested in the sales pitch. After presenting the problem, you can move on to the
solution to that problem. You will have to make a strong narrative with clarity and strong objectives.

WORKING ENVIRONMENT(JAN 2024)(10 MARKS)

From machine learning to data visualization, data science techniques are used to study the effects of
climate change on marine biology, land use and restoration, food systems, patterns of change in
vector borne diseases, and other climate-related issues.

The average American spends 2 hours each day social networking. That’s two hours worth of clicks,
views, likes, shares and comments that all go into massive databases to be culled for further analysis- to
better understand behaviors and improve the user experience, to create marketing profiles, to gather user
census data, and a lot more.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Not only do people spend a lot of time on social media, they seem to be comfortable revealing a lot of
personal information. Drunken weekends and parties, ditching work, relationship status updates, bragging
about indiscretions- some of the most intimate and embarrassing details about our lives end up on social
media networks for everybody you went to high school with to see.
But perhaps just as personal, and even less-often considered, is the information that social media
companies can glean from how users interact with the social media platform itself. Information like:
 What times and locations you access their system
 Who you interact with
 The type of devices you use
 What sort of media you view and how long you look at it
Data scientists are learning to tell surprisingly accurate stories about people from that accumulation of
information. There’s even speculation that your “Like” pattern on Facebook could give an astute data
scientist a fair approximation of your IQ.
A master’s-educated data scientist can not only weave all of that together for a personal portrait of an
individual, but can combine many such profiles to reveal a gestalt of the modern world: a living, breathing
perspective on the concerns, complaints, and obsessions of their audience.
That’s a powerful brew of data for everyone from online retailers to politicians. And social media
companies control the tap.
Reading the Tea Leaves: Extrapolating Personal Information from Seemingly Unrelated Data
The modern phenomena of social media is built almost entirely on a digital foundation. This makes it easy
to get numbers based on the actions and interactions of individuals online. But it takes a master’s-educated
data scientist to figure out how to tie these data points together in ways that are useful, interesting and
profitable.
In a 2014 interview with Christian Rudder, co-founder of online dating site OkCupid, he revealed that
profile data allowed the company to establish – with some 60 percent certainty – whether or not the
customer’s parents had been divorced before the customer was 21. Although the questions OKCupid uses
to establish a profile don’t explicitly ask for this information, the pattern of responses from apparently
unrelated questions was such that the inference could be drawn accurately.
Rudder believes that many personal traits have similar reveals. He also points out that data scientists at
social media companies have just begun to scratch the surface. Predictive algorithms are likely to improve
over time. And, though the mountain of data available to social networks may seem massive today, he
points out that the endless deluge of data that is coming will dwarf what is currently available as more and
more of our interactions move online.
With all that information at their fingertips, what will data scientists be able to learn about users as the
ability to digest endless troves of data advances?
Social Networks Aren’t Just Passively Gathering Information Anymore
Data scientists and researchers at social media companies benefit from having direct access to the code
base and the ability to update it frequently for their own purposes. They are not limited to piggy-backing
onto existing processes and hacking together instrumentation to imbue meaning—if they want a piece of
data collected regularly, they can create code to collect it.
A/B tests, in which different users are presented with slightly different versions of pages as a way to gauge
reaction, are trivial to set up. And, increasingly, machine learning that uses algorithms to improve data
collection and investigation feature prominently in data analysis at social media companies.
So simple curiosity has expanded data science at social media companies beyond marketing and into
peripheral fields like economics and identity.
This depth of insight and control makes some people uneasy.
In 2014 it was discovered that Facebook had been intentionally manipulating the news feeds it presented to
different users expressly to study their emotional reactions.
Scientists from Cornell and the University of California-San Francisco worked in conjunction with
Facebook to alter the text snippets posted in the news feeds of more than 700,000 users. Some were altered
to display more positive words; others to show more negative words. Subsequent posts from those user

SMVEC – COMPUTER SCIENCE AND ENGINEERING

 groups were then analyzed to determine whether or not the posts they read had altered their emotions in
line with the direction the news feed had been manipulated.
In itself, this is a fascinating use of data science in social experimentation, but it was also an ethical breach
that left users infuriated. Technically, it was fully in compliance with the company’s own privacy and fair
use policies, but that simply made matters worse in the mind of some critics: the organization appeared to
be legitimizing its right to arbitrarily mess with the heads of its users.
The future is sure to reveal more such quandaries about what personal privacy means in a data-rich
environment controlled by a private company. Data scientists and ethicists will have to work together
carefully to develop new standards and practices for responsible research.
One thing is certain. The scope of the revelations to be found in mining social network data is too valuable
to abandon. Data science has established itself as inseparable from social media processes.
Social Data Analytics Predates Even Dinosaurs Like Myspace
Social networks have been on the minds of researchers long before the Internet came along. Sociologists
were looking into the ways that people were tied together through their daily contacts and personal ties
way back in the 20th century.
By the 1970’s, practical applications for the research were being found as the terrorism threat began to rear
its head. Military and criminal justice analysts used social network theory to track terror cells and identify
high-value targets.
But it took the Internet to make this sort of analysis practical for private concerns since the military and
police had access to records – and the resources and capabilities to analyze them – that the private sector
did not. That is, until users started making their personal information available wholesale through social
networks.
Online dating sites might have been the first widespread efforts at social networking, but the concept
quickly blossomed into more generic sharing sites like Friendster and Myspace.
All those sites soon accumulated a wealth of data about their users, simply in the course of connecting
them to one another. But it might have been Facebook that really understood the implications of cleaning,
organizing and interpreting all that data.
Although the company was leery of diving immediately into selling advertising, founder Mark Zuckerberg
realized from the beginning that his company would be sitting on a treasure trove of data that advertisers
would be salivating over. But for the same reason, the information was vital to Facebook itself as a means
of measuring its own service and performance and catering to users.
So Facebook, Twitter, Instagram, and other prominent social media sites dove into Big Data almost
immediately for reasons identical to those of any other retailer: the better they understand their audience,
the more appealing they can make their product.

COLLECTING THE DATA

What is social media data?

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 platforms.
Social media data can also refer to data collected from content people post publicly on social media. This
type of social media data for marketing can be collected through social listening tools.

Why is social media data collection so important?

Like any business strategy, social media marketing is most effective when your goals and plans are based
on real data.
Social media data analytics provide information that helps you understand what’s working. Even more
important, you’ll see what’s not working, so you can make the right business decisions and refine your
strategy as you move forward.
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.
Here are some of the questions social media data mining can help answer:

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  What is the demographic profile of your following on each social platform?
 What times of day is your audience most active on social media?
 Which hashtags is your audience most likely to engage with?
 Does your audience prefer images or video posts?
 What kinds of content is your audience interested in?
 What subjects does your audience need help with?
 Which top-performing organic posts should you pay to boost?
You can also use social media to conduct A/B testing. This helps you refine your marketing message
element by element so you can increase your ROI.
Finally, social media data helps you prove the value of your social media efforts. With a proper data
collection in place, you can tie social media to real business results like sales, subscriptions, and brand
awareness.

What social media data should you track?

Which social media data you want to track will depend on your business goals.
If you want to use social media to build brand awareness, you might be most interested in tracking
engagement. If your goal is to create sales, you’ll likely want to track conversions.
Here is 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.
The first step to developing an effective social media data analysis plan is to establish SMART goals. Next
is to decide which data points you will track to measure progress towards your goals.
Here’s a rundown of how your goals, your social media data, and analytics all come together to form your
social media strategy:

How to track social media data for marketing

So, where can you get your hands on this data? Most social platforms have built-in analytics. These
provide basic data about your account performance and audience demographics.
But to get the most out of your social media data, it’s important to get a unified view. Here’s how to make
that happen.

Gather data with a social media data analytics tool

A social media analytics tool like Hootsuite Analytics gives you a full view of your social media data
across platforms. This provides important context for your data, as you can see how your audience
responds on different channels and refine your platform-specific strategy.
For larger social media marketing teams with more in-depth data analysis needs, Hootsuite Impact directly
tracks social media data to business goals and provides helpful competitive benchmarks.

Record your findings

Social media data collection efforts can be overwhelming if you don’t have a system for recording all the
information.
We’ve created a free social media data analysis template to track your data in an Excel spreadsheet or
Google Sheet. It allows you to record your social media data for multiple platforms and compare the
results to your target goals.

Share the results in a social media report

SMVEC – COMPUTER SCIENCE AND ENGINEERING

To use your social media data for marketing planning and analysis, you need to compile the data into an
easy-to-digest format that key stakeholders can understand.
Analytics programs like Hootsuite Analytics will create custom reports for you. Prefer to create your social
media report manually? We’ve got a free social report template you can use to create a professional
presentation of your social media data.

5 tips for smart social media data collection

1. Know your goals and KPIs

As we mentioned above, social media data is most useful when looked at in the context of real business
goals and key performance indicators (KPIs). When you have goals in place, you can use social media data
to track your progress and look for areas where you might need to improve.
But without goals in place, your social data lacks context. Sure, you’ll be able to see whether individual
data points are moving in a positive or negative direction. But you won’t be able to understand the big
picture.
Not sure where to start with goal-setting? We’ve got nine sample goals to get you started.

2. Track platform-specific social data

We’ve said social media data can give you a great unified view of your cross-platform social strategy. It
can also help you get really granular about your strategy for each social platform.
For example, you’ll start to see trends that guide you towards the best times to post on each of your social
accounts. (Hootsuite can help on this front with automated best-time-to-post suggestions based on your
own social media data.)
You’ll also start to understand your followers on each social media channel, which can help you
build buyer personas to better target your audience.

3. Set up a social listening program

Social listening can provide another set of social media data for you to draw from. The data we’ve talked
about so far comes in through your owned social properties. Social listening can help you discover data
from social media users who have no existing relationship with your brand.
It can also help put your social media data in context within your industry.
For example, social listening can provide data like:
 How many people are talking about your business or your products online (whether or not they
tag you in their posts)
 How many people are talking about your competitors
 What kinds of interests and concerns people express when talking about your industry on social
media
 How people feel about your latest product launch (a.k.a. sentiment analysis)
 Whether your competitors are running any promotions or launches you need to address
You can also get creative with your social listening strategies. Think about ways people’s social media
posts could help provide useful data for your business.
For example, researchers found they could use text social media data mining to predict morning traffic
patterns or gain insights into college students’ mental health. For businesses, social media data mining
can help predict demand and improve supply chain performance.
In one specific example, a study on social media data in Ottawa, Canada, found that social listening data
could be used to identify the attributes local residents find most important when recommending where to
buy fresh produce. This information could help guide local produce and grocery stores’ marketing
messages, or even store design.
Social listening provides valuable social data about existing communities online. According to
the Hootsuite Social Trends 2022 report:
“The smartest brands in 2022 will tap into existing creator communities to learn more about their
customers, simplify content creation, and build brand awareness and affinity.”

SMVEC – COMPUTER SCIENCE AND ENGINEERING

 The same report found 48% of marketers strongly agree social listening has increased in value for their
organization.

4. Ensure you comply with the rules

Data security on social media is not something to take lightly. More than a third of Internet users
worldwide (33.1%) have concerns about misuse of their personal data online.
If you work in a regulated industry, there are specific data privacy and compliance concerns you need to
manage. But privacy and data security are issues all social media managers should keep in mind.
For example, the Facebook Pixel is a useful tool for collecting social media data. It tracks conversions and
how people behave once they click through to your website. It uses cookies, so if you implement this tool,
you need to include a disclosure on your website telling people how you use cookies and share data
collected through them.
Privacy and data security requirements vary by region. Talk to your compliance or legal team about any
specific concerns, and be sure to review the terms of service for each social platform.

5. Focus on personalization (but not too much)

Social media data allows you to personalize social ads with strategies like remarketing or demographics
segmentation. But be careful not to go too far.
Half of U.S. internet users said brands using personal data in advertising helps them discover things they’re
interested in. And 49% said it makes it easier to find the products and services that most interest them. But
44% said this can feel invasive.
ANALYZING THE DATA

What is social media analysis?

Social media analysis is the process of collecting the most valuable data from your social media channels
and drawing actionable conclusions.
To get the most out of a social media marketing campaign, you need to analyse the data you gathered
during your previous activities.
You don’t have to run test campaigns before your big opening. Social media analysis is based on the data
you already have – from your previous posts, interactions with your followers, earlier social media
campaigns, and so on.
When it comes to social media analysis, you can base your data on two sources of information. As stated
above, you can take a deeper look at your own social media channels and analyse the results.
The second way to do a social media analysis is to analyse the social media presence of your
competitors. That will allow you to prepare a benchmarking dossier and you’ll have a general idea of what
works and what doesn’t in your industry.
Social media analysis will help you develop the most successful social media campaign. A campaign that
will reach the right audience, at the right time, and on the right channel.
To be fair, I have to admit – social media analysis is a time-consuming process. But the benefits of social
media analysis are hard to miss. That’s why, I’d love to dig a little deeper convince you to perform it
anyway.

How to perform social media analysis?

When it comes to social media analysis, there is a ton of information to gather and analyse.
And it’s impossible to collect some of the data without the help of a media monitoring tool.
Let’s take a look at what a media monitoring tool has to offer when it comes to social media analysis.
I’ll explore the topic of social media analysis based on Brand24, a top-notch social media listening tool.
Brand24 collects publicly available mentions from all major social media sites, including Facebook,
Instagram, Twitter, YouTube, TikTok, and Twitch.
Brand24 is verified by Facebook and is compliant with Facebook regulations and the GDPR.

How to start social media analysis?

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Start your social media analysis with creating a social media listening project. Enter the keywords you
want to monitor across different social media channels.
By creating at least a couple of projects with these keywords:
1. The name of your company – to monitor all the mentions about your company, even if the social
media users don’t add the @ sign
2. Your branded hashtag – to keep an eye on the spread of your message across social media. Brand24
will analyse the social media reach of the hashtag, sentiment around the conversation, type and
number of interactions, and will prepare a list of the most influential authors on Twitter.
3. Your campaign hashtag – to assess the performance of a social media marketing campaign within a
specified timeframe
4. A term related to your business – to find all the conversations around the topics you’re interested
in. For example, if I were an owner of a lipstick company, I would monitor keywords like
“lipgloss”; “gloss”; and “makeup”.
Social media monitoring tools don’t collect historical data, so the analysis process starts at the moment you
create a project. That’s why it’s vital to set up your project before you start a social media campaign.
Brand24 will provide the most valuable social media data to improve your social media strategy.

Which social media metrics should you follow?

The social media metrics important for your social media analysis depends on the goal you want to
achieve.
Tracking the changes in brand awareness requires different set if metrics that measuring the results of your
brand awareness campaign.
Another aspect you have to keep in mind is the quality of the metrics. A good social media analysis
provides very actionable social media insights. Focusing on vanity metrics won’t bring you far when it
comes to your social media strategy.
That being said, which social media metrics are vital for your social media analysis?

The volume of mentions

The volume of mentions will tell you how many times the name of your brand, your hashtag, or any other
keyword, was mentioned in a predefined time.

This is your starting metric when it comes to social media analysis. The ultimate goal of your social media
presence is to raise brand awareness — get your brand known across your existing and potential new
audience.
The more people talk about your brand, the higher the volume of mentions.

Sentiment
To correctly analyse the volume of mentions, you need some additional sets of data. One of them is the
sentiment around your mentions.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Social media sentiment analysis will tell you how social media users feel about your brand. If you see a
sudden spike in negative mentions about your brand, product, or service, it might indicate a social media
crisis in the making.

Social media and non-social media reach

You might wonder why should you take non-social media reach while talking about social media analysis.
The reach of your posts, both social and non-social, will indicate where your audience is present and what
type of content they expect to see from your brand.
First, compare non-social reach to social reach. The comparison will tell you whether your audience reacts
to social media content. Should you put more time and effort into establishing a robust social media
presence or are there any lower hanging fruit?

If your social media accounts don’t generate social media buzz, you may want to consider two options.
First, you can work on establishing your online presence. Create interesting content, interact with your
followers, run social media marketing campaigns. These activities will bring, over time, dedicated
followers.
If time is of the essence, you could try working with social media influencers. The key to a successful
cooperation with an influencer is to choose the right one. Ideally, this person will be able to reach audience
similar to yours and will act as an authority figure.

The share of voice

The share of voice is one of the most important social media metrics.
The share of voice tells you what percentage of the whole online discussion was initiated by a given social
media account.

The higher the share of voice, the more influential your social media account is. Your potential customers
will consider your brand as an industry leader, which will, ultimately generate new leads.

What are the benefits of social media analysis?

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Information is power. The more actionable insights you can collect, the better campaign and general social
media presence you’ll be able to develop.
Therefore, social media analysis should be an incremental part of your marketing planning.

What exactly are the benefits of social media analysis?

Measure the social media ROI

That’s one of the biggest challenges awaiting social media managers.
How should you calculate the ROI of your social media marketing presence?
Which social media metrics you want to focus on, depends on your social media goal. Identifying sales
from your social media channel requires a different metric than measuring brand awareness.
Nevertheless, in every case, it’s necessary to assess the impact of your marketing activities.
Estimating the social media reach, analysing the number and type of interactions, assessing the sentiment
around your content, tells you whether you’ve reached the right audience.

If the results of your social media analysis aren’t satisfactory, you should implement changes to your
marketing tactics.
An exhaustive social media analysis of your marketing activities is not a mumbo jumbo but solid data you
could base actionable actions upon.
The figures will indicate the effectiveness of your social media marketing campaign and provide insights
into how to improve your social media presence.

Improve your social media strategy

Analysing the results of social media activities can also have a positive impact on enhancing your social
media strategy.
The results of social media analysis indicate which social media channels will bear the fruit and deliver
your social media ROI. After all, there is no point in investing your time and effort into channels where
your message won’t be heard.
Another benefit of social media analysis is the ability to create better content. And by better content, I
mean content that is attractive and engaging to your audience. Content that will bring you new leads.
Social media algorithms favoured content that sparks interactions. The more likes, shares, or comments
your photos, films, or posts generate, the better.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Social media analysis will tell you which type of content should you focus on.
Social media analysis numbers will help you get an understanding on how your company is seen on social
media and what can you do to refine your image.

Understand your audience

To build a robust social media presence you need to reach the right people on the right platform. Without
compelling content, it will be hard to engage your audience.
Part of building your content strategy is understanding your audience. Once you know who you are talking
to, preparing attractive content will be a piece of cake.
By performing social media analysis you will know who interacts with your content.
You will be able to prepare content, for example, photos, films, gifs, ebooks, reports, (the sky is the limit in
that case) that engages your audience. That will not only look good on your social media analysis graphs,
but will also have a positive effect on your social media goals.
Social media users leave a ton of information on social media, conducting a social media analysis will
provide all the data you need legally and ethically.

Spy on your competitors

Being one step ahead of your competitors isn’t always easy.
One of the vital steps in becoming an industry leader is knowing what your rivals are up to.
Social media competitors’ analysis highlights any differences between you and your main competitors. The
analysis pinpoints both your advantages and disadvantages.
You can leverage your position by emphasizing your strengths and trying to exploit your rivals
weaknesses.
Imagine the situation where your competitors could ignite a conversation on one of their channels or
consistently post content that users gladly engage with.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Compare marketing results to get the most out of social media analysis.
Social media analysis will help identify the posts that generate the most interactions. By studying the posts,
you can try to emulate the results or even adjust them to improve the results.
Moreover, if you take a step back, social media analysis will help you identify social channels that are the
most efficient for your business. It will save a lot of experimenting as you will be able to develop a more
thoughtful and detailed social media strategy.

Prepare a benchmarking dossier

Benchmark dossier is directly related to social media competitor analysis.
In order to know whether your campaign is performing well, you need a point of reference. Analysing in-
depth the social media presence of your competitors will provide all the necessary data.
Analyse the average social media metrics on which you want to base your campaign. The median will give
you a general idea on how your social media campaign stands in your industry.

Establish the direction in which your industry is headed

Social media analysis will not only provide insights into the current state of your industry, but could also
pinpoint the direction in which your industry is headed.
How can you do that?
By analysing the general talk around your business niche, monitoring what your customers need and what
improvements they would add to your product or service.

The customers shape your industry. If your product doesn’t meet their needs, they will look for alternative.
Customers suggestions will give you a general idea where your industry is headed. Picking them up before
your competitors will make you an industry leader and could increase your market share.

What pieces of information will social media analysis provide?

That’s a lot when it comes to the benefits of social media analysis but what information exactly should you
look for?
Social media analysis should give you answers to these questions:

SMVEC – COMPUTER SCIENCE AND ENGINEERING

 Who is your desired audience?
Think about the demographic information, such as gender, education, employment information, age, place
of residence, hobbies, and interests.

What are their preferred social media channels?

Is it wise to invest in a TikTok marketing strategy? Maybe the majority of your audience is active on
Twitter? Social media analysis will provide answers to these questions.

What type of content resonates best with your target audience?

Are they interacting more with photos or videos? What type of content your audience shares most often?

Who are industry influencers you should keep an eye on?

Influencer marketing is one of the most powerful form of marketing campaigns. The key to a successful
influencer marketing campaign is choosing the right person to work with. Take a look at people who
already are talking about your business niche and determine the right fit for you.

What is the social media reach of posts?

Answering this question will not only help you determine the success of your posts. By analysing the
social media reach of your competitors’ posts you’ll be able to assess the marketing efforts of your
competitors.

Why is social media analysis a necessary part of your marketing strategy?

If you can measure your marketing activities, you can improve them. Since the social media landscape is
constantly changing, it’s important to keep up-to-date.
Even slightest changes in social media algorithms could have tremendous impact on your social media
presence. Analysing the effects of your social media activities could help you prevent drops in social media
engagement.
You will be able to spot seasonal changes and distinguish them from real problems with social media
strategy. In the constantly changing social media world, keeping your finger on the pulse will help you
reach your marketing goals. Social media analysis will help you be the industry leader.
VISUALIZING THE DATA
By using data visualization, they can increase the quality and speed of their social media marketing
decisions. They’ll be able to understand massive amounts of information better, make informed
decisions, as well as present the results to clients, executives, or managers in a clear and pleasant-to-look
manner.

What is data visualization?

It is the graphical representation of data by using graphs, charts, maps, and other visual elements that can
be easily interpreted by everyone. In a way, it’s a type of visual art that attracts people’s attention and
keeps their eyes on the most important message.
Data visualization helps decision-makers understand difficult concepts or discover new patterns. The most
common forms include:
• Bar charts
• Line charts
• Area charts
• Pie charts
• Histograms
• Scatter plots
• Heat maps

SMVEC – COMPUTER SCIENCE AND ENGINEERING

It’s important to use the right type of data visualization that will help you point out and clarify the
takeaways from your data instead of confusing others even more.

Is data visualization in demand?

Data visualization can improve your marketing efforts in many other ways than just making data easier to
understand. Here are some of the biggest reasons why it’s in demand:
It provides greater insight
Data visualization improves comprehension by helping you to figure out the connection between various
datasets to identify patterns and trends. It makes your data more meaningful and relevant, helping you to
apply it correctly.
It connects and presents the most important parts of a dataset in a clear way that makes sense to anyone
who sees it, rather than overwhelming you with information.
Thanks to these insights, you can make a difference between seemingly similar data, something that you
can do with traditional descriptive statistics.
It helps you make data-driven decisions
Data visualization helps you make informed, data-driven decisions by providing better insight and
understanding of the data. As a result, decision-makers save a significant amount of time and energy that
would otherwise be spent sifting through massive amounts of data.
Instead, they can focus on developing successful campaigns and strategies to beat the competition and stay
ahead of them.
It grabs your audience’s attention
Well-designed visuals along with data storytelling grab your audience’s attention and engage them. It
makes the information you present more meaningful, helping you to understand the message.
It can be repurposed
Thanks to its versatility, data visualization can be repurposed into various formats and aspects of business,
whether that’s content marketing or social media. Presenting the information in a clear way that’s easy to
understand improves the comprehension of important metrics.
Now that you know the pros of data visualization and why it is in demand, let’s see what social media data
is and how it can be applied to data visualization here.

What’s social media data?

Likes and shares are just part of social media data. What this valuable data does is help you to understand
your audience better and their engagement with your brand. Collecting and analyzing social media data
allows you to see how successful your campaigns and posts are.
Thanks to social media analytics, you can find out the type of content that converts and the platform that
brings the most leads. Besides measuring impressions, likes, and shares, social media data can be used for:
• Lead generation – Social media data analytics allows you to create an accurate lead generation model
based on the activities that social media users engage in.
• Sales outrich – Social media insights can help salespeople connect with customers more easily through
personalized conversations and use the right sales approaches to achieve their goals.
• Audience segmentation – Social media analytics allows you to segment your audience based on things
like gender, age, occupation, ethnicity, and other demographic segmentation factors.
• Content engagement – Social media data can help you understand where to post more so that you can
engage with your audience, as well as where to post less.
The three steps of social media analytics are:
1. Capturing – determining a particular goal and capturing data to measure your social media key
performance indicators.
2. Comprehending – determining the most effective tactics on particular networks. An audience that
doesn’t interact with your content means that you have to improve your strategy.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

3. Presenting – Once you comprehend your data, the next step is to visualize it and present it. For this, you
need data visualization.

How to visualize social media data - tips

When it comes to presenting social media data, here are the best tips that are worth remembering:
1. Know your audience
Adapt your presentation to your target audience, whether it's executives, coworkers, or stakeholders. This
is crucial if you want to engage them effectively. It’s similar to knowing your audience on social media so
that you can deliver the right content for them and ensure high engagement.
Think about your audience when creating visual formats to present your social media data. For example,
you wouldn’t like to overwhelm your executives with information as you already know that they are busy.
If your social media data visualization is aimed at a director who would like to know the high-level key
performance indicators and the particular figures that caused them, create a table that compares precise
values. Even though this type of visual may not be as attractive as infographics, they offer hard data on
metrics like conversions, leads, etc.
As you can see, knowing your audience can help you tackle the right data that will be interesting and
relevant to them. Avoid overwhelming them with information even if you present the most relevant data.
Also, make sure you have an idea of the story you want to share.
Therefore, determine a precise purpose for your visualized social media data to narrow it down to one
important subject that you want to talk about. In this way, you can group and organize information in a
logical and easy-to-understand order for effective and powerful data storytelling.
2. Know your graphs
Each graph is created to present data in a specific way, so it’s only logical that some of them are better than
others. Take a look at the different types of graphs and their common usage:
• Scatter plot – this type of graph shows a correlation.
• Pie chart – this one shows proportions. However, make sure you don’t use it when you have more than 5
slivers. In that case, use another graph.
• Line graph – use this graph to present trends and patterns.
• Table – this type of graph is perfect for presenting specific values.
• Bar chart – this one is excellent for showing comparisons.
For example, a pie chart is great for presenting how the budget for an ad campaign on social media is being
used. This type of graph shows how much money is being spent and where.
3. Don’t use just any color
When it comes to colors, it’s best to start your graphs in black and white, and then gradually add colors
when needed. Even though using many different colors is fun and can make the graphs look entertaining, it
can be counterproductive.
That’s because a graph with too many colors can distract your audience and confuse them instead of
helping them understand the information presented. The purpose of graphs is to present the information as
clearly as possible, and colorful graphs don’t deliver this impression.
Therefore, you may want to know the following things when using colors in your graphs:
• Avoid red whenever possible – This color has a negative connotation for you. When people see red, they
instantly connect it to something bad or wrong, even if it’s used to point out something positive, like a rise
in Facebook engagement.
• Color gradients for time series – you can use the lightest to darkest shades of one color to present
certain data from the past to the present. Fading colors can signify less relevant information as the years go
by.
• Highlight – if you want to point out a specific value so that everyone notices it, use a strong hue. You
can use it, for example, to highlight a surge in click-throughs.
• Assign value to each color – if you want to represent a range with the help of colors, choose colors and
give each of them a specific value. For instance, yellow for anything over 80%, and blue for anything
below 20%.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

 • Use color to present a group of relevant data – use one color, for example, blue for Facebook or
orange for Instagram, to group relevant social media data together.
• Use brand colors – in this way, you’ll avoid using too many colors and making the graph confusing.
4. Make it simple
When it comes to presenting your data in a visual format, it’s important to consider the user's experience.
To provide data insights effectively, you’ll have to take an audience-centric approach.
For that purpose, take the following things into consideration:
• Left to right – that’s how our minds work, especially when we see charts that compare values.
Therefore, present the values in a descending or ascending order to ensure easy comparison.
• Do the job for your audience – this includes sorting data into a logical order, grouping relevant values
together, and highlighting important parts.
• Do not focus on the aesthetics too much – avoid using too many colors, even if that will make your
graph more vibrant and attractive. Don’t use a pie chart when you can just write out numbers.
• Less is more – don’t use logos, imagery, and clipart as that will only make your presentation confusing.
Keep it simple.
5. Use the right tools
There are numerous data visualization tools available, but using the right one, such as Whatagraph, can
assist you in making sense of your data and clearly presenting social media metrics so that your audience
understands them easily.

GETTING STARTED WITH THE TOOLSET.

Why you need social media analytics tools

Social media analytics tools help you create performance reports to share with your team, stakeholders, and
boss — to figure out what’s working and what’s not. They should also provide the data you need to assess
your social media marketing strategy on both macro and micro levels.

10 of the best social media analytics tools

Social media analytics tool 1: Hootsuite Analytics

Key benefits: Performance data from every social network in one place with easy-to-understand reports
Paid or free? Paid tool
Skill level: Beginner to intermediate
Best for: Business owners who run their own social media, social media managers at small-to-medium
sized businesses, marketing teams
Most social media management platforms have built-in analytics tools. We hope you’ll forgive us for
saying Hootsuite’s reporting capabilities are our favorite. But it’s the tool we know and love best.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Imagine Twitter analytics, Instagram analytics, Facebook analytics, Pinterest analytics, LinkedIn analytics
all in one place. Hootsuite Analytics offers a complete picture of all your social media efforts, so you don’t
have to check each platform individually.
It saves time by making it easy to compare results across networks.
Social posts metrics:
 Clicks
 Comments
 Reach
 Engagement rate
 Impressions
 Shares
 Saves
 Video views
 Video reach
 And more

Profile metrics:
 Follower growth over time
 Negative feedback rate
 Profile visits
 Reactions
 Overall engagement rate
 And more

Best time to post recommendations:

Ever spend a bunch of time writing and designing a social post only to have it fall completely flat? There
could be a lot of reasons for that. But one of the most common reasons this happens is posting at the wrong
time. A.k.a. Posting when your target audiences are not online or not interested in engaging with you.
This is why our Best Time to Publish tool is one of the most popular features of Hootsuite Analytics. It
looks at your unique historical social media data and recommends the most optimal times to post based on
three different goals:
1. Engagement
2. Impressions
3. Link clicks

Most social media analytics tools will only recommend posting times based on engagement. Or they’ll use
data from universal benchmarks, instead of your unique performance history.
Other cool things you can do with Hootsuite Analytics:
 Customize report templates for only the metrics you care about
 Get reports on your competitors

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  Track the productivity of your social team (response times, and resolution time for assigned
posts, mentions, and comments)
 Monitor mentions, comments, and tags related to your business to avoid PR disasters before they
happen

Social media analytics tool 2: Google Analytics

Key benefit: See how much traffic and leads flow to your website from your social media channels
Paid or free: Free tool
Skill level: all skill levels
Best for: all social media professionals should be familiar with Google Analytics, but especially those who
work for a web-based business

You’ve probably heard of Google Analytics already. That’s because it’s one of the best free tools to use to
learn about your website visitors. And if you’re a social marketer who likes to drive traffic to your website,
then it’s an invaluable resource to have in your back pocket.
While it’s not a social media reporting tool per se, you can use it to set up reports that will help you:
 See which social media platforms give you the most traffic
 See what content drives the most leads and traffic on which social networks
 Get to know your audience with demographic data
 Calculate the ROI of your social media campaigns

With these data points, you’ll be able to get the most out of your social media campaigns and effectively
strategize for the future. No social media strategy is complete without Google analytics.

Social media analytics tool 3: UTM parameters

Key benefit: See how much web traffic and conversions your social media channels and campaigns
generate (to be used with a web analytics platform like Google Analytics).
Paid or free: Free tool
Skill level: intermediate
Best for: all social media managers

UTM parameters are not a standalone social media analytics tool, but they are essential in helping you set
up Google Analytics (or another web analytics platform) to best measure social performance.
Put simply, UTM parameters are short pieces of code appended to the links you share on social media.
They very precisely tell you how many people interact with your content and end up on your website.
In the screenshot above, the UTM parameter is everything that comes after the question mark.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

UTM parameters aren’t essential if you’re only concerned about reporting on social media performance in
terms of engagement, followers, etc. But if you want to take it to the next level, UTM parameters + Google
Analytics will give you more precise data on which social media content and channels drive traffic and
conversions.
Pro tip: You don’t need to know how to write code to include them on your social media posts. If you use
a social media management platform like Hootsuite, you can automatically generate UTM parameters in
seconds.

Social media analytics tool 4: Hootsuite Insights powered by Brandwatch

Key benefits: Analyze brand sentiment and customer demographics in real time, alongside all your other
social media performance data
Free or paid: Paid tool
Skill level: Intermediate to advanced
Best for: Social media professionals, PR and communications teams, small to large social media teams
Hootsuite Insights is a powerful enterprise-level social listening tool that doubles as an analytics tool.
It goes beyond Hootsuite Analytics, tracking your earned social mentions so you can measure social
sentiment and improve customer experience.

It also analyzes data about your audience demographics like gender, location, and language. You can
compare demographics across networks, or look at the aggregate picture of your audience for all networks
combined.
This is a tool that really tells you a lot about your audience — and how they feel about you. It can tell you
whether a spike in mentions is a victory or a disaster. And it can help you capitalize or avoid either one,
respectively.

Social media analytics tool 5: Brandwatch

Key benefits: Track and analyze data from more than 95 million sources, including blogs, forums, and
review sites, as well as social networks
Free or paid: Paid tool
Skill level: Beginner to intermediate
Best for: PR and communications teams, social media marketers who focus on engagement and brand
monitoring
Brandwatch is a powerful tool with five easy-to-use social media analytics report templates:
 Summary: A high-level view of social conversations about your brand, competitors, or
keywords.
 Trends: A report on the conversations and accounts influencing a specific topic or hashtag,
including mentions per hour or minute.
 Reputation: A checkup on sentiment trends you might need to monitor or address.
 Influencers: A report to help you identify influencer marketing opportunities relevant to your
brand and analyze their activity. 

SMVEC – COMPUTER SCIENCE AND ENGINEERING

  Competitor comparison: Benchmarking social media data for conversation volume, sentiment,
and share of voice.

Social media analytics tool 6: Talkwalker

Key benefits: Monitor conversations from more than 150 million sources to analyze engagement, potential
reach, comments, sentiment, and emotions
Free or paid: Paid tool
Skill level: intermediate to advanced
Best for: social media managers, PR and communications teams, brand monitors, product marketers,
researchers
Talkwalker offers analytics related to social conversations beyond your owned social properties, including:
 Mentions
 Brand sentiment 
 Important influencers
 Author lists
You can filter by region, demographics, device, type of content, and more.
Talkwalker is especially useful to spot activity peaks in conversations about your brand. This can help you
determine the best times for your brand to post on social media.

Social media analytics tool 7: Hootsuite Impact

Key benefits: Track how organic and paid social impact real business goals and get recommendations for
how to improve
Free or paid: Paid tool
Skill level: intermediate to advanced
Best for: social media teams at enterprise organizations with lots of moving parts, paid social advertising
teams
Hootsuite Impact provides an in-depth look at the performance of your organic and paid social posts. It
then compares that performance to specific business goals, like sales and leads generated. Next, it
recommends actions to improve your results.
Hootsuite Impact integrates with tools like Google Analytics, Adobe Analytics, and your ad accounts on
many differt social platforms. This gives you a full picture of your post and campaign results, all in one
place. With organic and paid analytics side-by-side, you don’t have to gather data from separate tools to
create a social media analytics report.
Instead, you see exactly how much revenue all your social efforts generate, so you can prove your social
ROI. Keep in mind that ROI is not only about sales generated. Hootsuite Impact uses a custom ROI
formula developed specifically for your business. Seeing which of your efforts have paid off has never
been easier.
You’ll also get a clear breakdown that shows you exactly how to replicate your successes and improve in
the areas where you’re falling short.
Then there’s the competitive benchmarks. To get the best insights from social analytics, you need to
understand how other businesses in your industry compare. Hootsuite Impact shows how your results stack
up against your competitors, so you can spot opportunities to improve.

Social media analytics tool 8: Channelview Insights

Key benefits: Analyze the YouTube performance of multiple channels
Free or paid: Paid tool (free for Hootsuite Enterprise users)
Skill level: all skill levels
Best for: YouTube marketers and creators, social media managers who run a YouTube channel alongside
other social channels
The Channelview Insights App adds YouTube analytics to the Hootsuite dashboard.
With this integration, you can analyze your YouTube video and channel performance alongside all your
other social media channels. You can also schedule automatic, regular reports.

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Easily see the following metrics in one place:
 Views, engagement, subscription activity
 Video traffic sources
 Audience insights for demographics, geography, acquisition and more

Social media analytics tool 9: Mentionlytics

Key benefit: Track mentions, keywords, and sentiment across multiple languages on social channels and
elsewhere on the web.
Free or paid: Paid tool
Skill level: Beginner to intermediate
Best for: PR and communications teams, brand monitoring teams, product marketers, researchers at small
to medium-sized businesses.
Want to get a big picture view of what’s being said about your brand on the internet? Mentionlytics is a
great entry into the world of social media monitoring — especially if you run a global business in more
than one language.

Other things you can do with Mentionlytics:

 Sentiment analysis
 Find top influencers that follow you
 Filter results by keywords
 Reply to mentions directly

Social media analytics tool 10: Panoramiq Insights

Key benefit: tracks Instagram analytics, including Instagram Story analytics
Free or paid: Paid (or free for Hootsuite Enterprise users)
Skill level: All skill levels

SMVEC – COMPUTER SCIENCE AND ENGINEERING

Best for: Instagram marketers
Alert all the Instagram marketers. Panoramiq Insights is perfect for Hootsuite free users or pro users who
want to get deeper insights on their Stories in particular. (Just download the app from our App Library).

Among other things, Panoramiq Insights lets you:

 Analyze follower demographics, including age, gender, country, city and language
 Monitor Instagram account activity (for up to two accounts), including views and new followers
 Find your best posts with view and engagement analytics
 Measure Story views and interactions

SMVEC – COMPUTER SCIENCE AND ENGINEERING