Sentiment Analysis of Product Based Reviews Using Machine Learning Approaches

ABSTRACT

Sentiment analysis or opinion mining is the computational study of people’s opinions,

sentiments, attitudes and emotions expressed in written language. Create word net
dictionary is all positive words are written out separately and all negative words are
written out at one place. Extraction of dataset is First dataset of publicly available
product reviews were downloaded from the internet and then the passage extraction
framework identifies important sections of the text which is most representative of the
content of the document. More specifically, involves identifying and extracting those
specific product features and the opinions on them.
S. No. CONTENT PAGE. NO

INTRODUCTION

01. 1.1 COMPANY PROFILE 2

1.2 PROJECT OVERVIEW 4

SYSTEM ANALYSIS

2.1 FESIBILITY SYSTEM 7

02.
2.2 EXISTING SYSTEM 8

2.3 PROPOSED SYSTEM 10

SYSTEM CONFIGURATION

3.1 HARDWARE SPECIFICATION 12

03.
3.2 SOFTWARE SPECIFICATION 14

3.3 ABOUT THE SOFTWARE 15

SYSTEM DESIGN

4.1 NORMALIZATION 26

04. 4.2 TABLE DESIGN 27

4.3 INPUT DESIGN 35

4.4 SFD/DFD 38

05. SYSTEM DESCRIPTION 45

06. TESTING AND IMPLEMENTATION 54

07. CONCLUSION AND FUTURE SCOPE 58

08. FORMS AND REPORT 60

09. BIBLIOGRAPHY 67

CHAPTER-1
INTRODUCTION
Social media website is defined as “a website that facilitates meeting people, finding like
minds, communicating and sharing content, and building community”; this kind of website
allows or encourages various types of activities, such as commercial, social, or a combination
of the two. Social media categories include digital library, e-commerce, entertainment, forum,
geolocation, social bookmark, social review, social game, and social network. Social network
is the subcategory of social media, which is the social structure of people who are joined by
common interest. Social media are social channels of communication using web- based
technologies, desktop computers, and mobile technologies. These technologies create
highly interactive platforms through which individuals, communities, and organizations can
share information, discuss, rate, comment, and modify user-generated and online contents.
These advancements enable communication among businesses, organizations, communities,
and individuals. Social media technologies change the way individuals and large
organizations communicate, and they are increasingly being developed.

Wide range of applications in business and public policy uses sentiment analysis. Sentimental
analysis is now being used from specific product marketing to antisocial behaviour
recognition. Businesses and organizations have always been concerned about how they are
perceived by the public. This concern results from a variety of motivations, including
marketing and public relations. Before the era of Internet, the only way for an organization to
track its reputation in the media was to hire someone for the specific task of reading
newspapers and manually compiling lists of positive, negative and neutral references to the
organization, it could undertake expensive surveys of uncertain validity. Today, many
newspapers are published online. Some of them
publish dedicated online editions, while others publish the pages of their print edition in PDF.
In addition to newspapers, there are a wide range of opinionated articles posted online in
blogs and other social media. This opens up the possibility of automatically detecting positive
or negative mentions of an organization in articles published online, thereby dramatically
reducing the effort required to collect this type of information. To this end, Organizations
are becoming increasingly interested in acquiring fine sentiment analysis from news articles.
Fine- grained sentiment analysis is an extremely challenging problem because of the variety
of ways in which opinions can be expressed. News articles present an even greater challenge,
as they usually avoid overt indicators of attitudes. However, despite their apparent neutrality,
news articles can still bear polarity if they describe events that are objectively positive or
negative. Many techniques used for sentiment analysis involve naïve approaches based on
spotting certain keywords which reveal the author or speaker‟s emotions. We use naïve
performs fine-grained sentiment analysis to classify sentences as positive, negative or neutral.

Levels of Sentiment Analysis

 Document level Sentiment Analysis

In this Sentiment Analysis level whole document has analyzed and classify whether a
whole opinion document expresses a positive or negative sentiment. In one document only
reviews of one product has been reviewed. And task is to find out the opinion about that
product. So this task is broadly known as document-level sentiment classification. In this
level, expressed opinion is on single entity. This is not applicable when there is document
which contains multiple product reviews.
  Sentence Level Sentiment Analysis

In this level, task goes to every sentence and determine whether the sentence
expresses the positive, negative or neutral opinion. This level attentively related to
Subjectivity Classification, which distinguishes objective sentences and subjective sentences.
Objectives sentences express factual information about sentences where Subjective
sentences express the subjective information about sentences. Many objective sentence can
involve opinions. This task is known as Sentence Level Sentiment Analysis.

 Aspect level Sentiment Analysis

Aspect Level sentiment Analysis was earlier called Feature level (feature-based
opinion mining and summarization) Sentiment Analysis. Document and Sentence Level
Sentiment Analysis do not find out what exactly people like or did not like. It achieves finer-
grained analysis. In this level directly looks at the opinion itself instead of looking to
documents, paragraphs, sentences, clauses or phrases. This level consider the entity, aspect of
that entity, opinion of aspect, opinion holder and time. Because of these parameters this
level can find what actually people like means which feature of product mostly likes by
customers and also on which time. This task is more interesting and more difficult too.
 CHAPTER 2 LITERATURE
SURVEY
Literature survey is the most important step in software development process. Before
developing the tool it is necessary to determine the time factor, economy and company
strength. Once these things are satisfied, then the next step is to determine which operating
system and language can be used for developing the tool. Once the programmers start
building the tool the programmers need lot of external support. This support can be obtained
from senior programmers, from book or from websites. Before building the system the above
consideration are taken into account for developing the proposed system.

The major part of the project development sector considers and fully survey all the
required needs for developing the project. For every project Literature survey is the most
important sector in software development process. Before developing the tools and the
associated designing it is necessary to determine and survey the time factor, resource
requirement, man power, economy, and company strength. Once these things are satisfied
and fully surveyed, then the next step is to determine about the software specifications in
the respective system
such as what type of operating system the project would require, and what are all the
necessary software are needed to proceed with the next step such as developing the tools, and
the associated operations.

„J. Serrano-Guerrero et al [1] states that Today, Digital Libraries 2.0 depends on client
connections through coordinated efforts, for example and wikis. Today, language
transmission frameworks with Google Wave are required for the purpose of speaking with
specialists inspired by the field of exploration. This framework takes into consideration the
formation of a typical space through waves for of joint effort and trade of thoughts between
numerous scientists intrigued by a solitary theme. One of the fundamental impacts of this
technique is hard to foresee. Z. Zhang et al [2] the review consolidates client focused
substance and channel based coordinated effort with fluffy innovation and fosters an
incorporated way to deal with item-based administrations.

Z.B. Sun et al [3] in this article he explains, we recommend ways of incorporating data, for
example, web-based media to profit from the warning framework. is. The connection
between the two clients and the meaning of the mark are utilized to decide the
misrepresentation in the network of the client object. Specifically, we utilize a two-bunch
calculation to decide the fitting gathering to create various cravings. Investigation dependent
on genuine numbers shows that the normal technique accomplishes preferred outcomes over
existing strategies. Notwithstanding, this strategy has its limits and shortcomings, which
should be tended to. Another obstacle isn't knowing whether two distinct things are
addressed by a similar name.

H.L. Zheng et al. The subject of how to work on the realness of the store network has turned
into a significant issue in modern examination. Numerous models have been approached to
resolve this issue, yet frequently center around a similar idea. In contrast to great work, in this
review, we request a method for giving input blended in with the interpersonal organization
of shoppers. The proposed technique enjoys numerous upper hands over typical
arrangements. To begin with, it gives a solid two-venture process for distinguishing clients
involving direct trust between clients in the informal community and defining limits. Second,
create the conventional sifting technique in light of the Pearson
coefficient to lessen the worth of the forecast. Third, it fuses Individual Effects into the CF
framework to further develop proficiency. Here we use network techniques. There is a
method for tackling this issue notwithstanding other data, since it is extremely challenging to
comprehend the issue that will be brought by clients who are beginning to freeze.

L.O. Colombo-Mendoza [5] clarified that internet business verification is a generally

involved strategy for selling items and fulfilling clients. This article examines the Hybrid way
to deal with web-based business counseling. This Hybrid methodology has been acquainted
with address the issue of the customary counseling framework. In outrageous cases, the
advocate doesn't fit the unexpected however proper support; Customers' thoughts and
thoughts ought to be added together effectively use-history

CHAPTER 3
METHODOLOGY

3.1 EXISTING SYSTEM

 E-commerce reviews reveal the customers‟ attitudes on the products, which are very
helpful for customers to know other people‟s opinions on interested products.
Meanwhile, producers are able to learn the public sentiment on their products being
sold in E-commerce platforms.
 Generally, E-commerce reviews involve many aspects of products, e.g., appearance,
quality, price, logistics, and so on.
  Therefore, sentiment analysis on E-commerce reviews has to cope with those
different aspects.
 The problem with public auction is that the participation of the general public
is very limited.

3.2 DISADVANTAGES OF EXISTING SYSTEM

 Cyber Bullying
 Higher Risk of Fraud and identity Theft
 Privacy issues
3.3 PROPOSED SYSTEM

 Recommender System (RS): Special type of information filtering system that

provides a prediction that assists the user in evaluating items from a large collection
that the user is likely to find interesting or useful.
 Status update (micropost): Short message, shared in an online social platform,
expressing an activity, state of mind or opinion.
  Folksonomy: Whole set of tags that constitutes an unstructured collaborative
knowledge classification scheme in a social tagging system.
 This step involves identifying and extracting those specific product features and the
opinions on them.
 The aim of the project is to socialize the auction so that people from far &
wide and even across the continent can participate in it.

3.4 ADVANTAGES OF PROPOSED SYSTEM

• It is easily understand the similarities between user and system.

• It is easy to segregate groups with similar traits and assign them into clusters.

3.5 SOFTWARE ENVIRONMENT

Python:

Python is a high-level, interpreted, interactive and object-oriented scripting language. Python

is designed to be highly readable. It uses English keywords frequently where as other
languages use punctuation, and it has fewer syntactical constructions than other languages.

 Python is Interpreted − Python is processed at runtime by the interpreter. You do

not need to compile your program before executing it. This is similar to PERL and
PHP.

 Python is Interactive − You can actually sit at a Python prompt and interact with the
interpreter directly to write your programs.
  Python is Object-Oriented − Python supports Object-Oriented style or technique of
programming that encapsulates code within objects.

 Python is a Beginner's Language − Python is a great language for the beginner-level

programmers and supports the development of a wide range of applications from
simple text processing to WWW browsers to games.

History of Python

Python was developed by Guido van Rossum in the late eighties and early nineties at the
National Research Institute for Mathematics and Computer Science in the Netherlands.

Python is derived from many other languages, including ABC, Modula-3, C, C++, Algol-68,
SmallTalk, and Unix shell and other scripting languages.

Python is copyrighted. Like Perl, Python source code is now available under the GNU
General Public License (GPL).

Python is now maintained by a core development team at the institute, although Guido van
Rossum still holds a vital role in directing its progress.

Python Features

Python's features include −

 Easy-to-learn − Python has few keywords, simple structure, and a clearly defined
syntax. This allows the student to pick up the language quickly.
  Easy-to-read − Python code is more clearly defined and visible to the eyes.

 Easy-to-maintain − Python's source code is fairly easy-to- maintain.

 A broad standard library − Python's bulk of the library is very portable and cross-
platform compatible on UNIX, Windows, and Macintosh.

 Interactive Mode − Python has support for an interactive mode which allows
interactive testing and debugging of snippets of code.

 Portable − Python can run on a wide variety of hardware platforms and has the same
interface on all platforms.

 Extendable − You can add low-level modules to the Python interpreter. These
modules enable programmers to add to or customize their tools to be more efficient.

 Databases − Python provides interfaces to all major commercial databases.

 GUI Programming − Python supports GUI applications that can be created and
ported to many system calls, libraries and windows systems, such as Windows MFC,
Macintosh, and the X Window system of Unix.

 Scalable − Python provides a better structure and support for large programs than
shell scripting.

Apart from the above-mentioned features, Python has a big list of good features, few are
listed below −
  It supports functional and structured programming methods as well as OOP.

 It can be used as a scripting language or can be compiled to byte- code for building
large applications.

 It provides very high-level dynamic data types and supports dynamic type
checking.

 It supports automatic garbage collection.

 It can be easily integrated with C, C++, COM, ActiveX, CORBA, and Java.

Python is available on a wide variety of platforms including Linux and Mac OS X.

Let's understand how to set up our Python environment.

Getting Python

The most up-to-date and current source code, binaries, documentation, news, etc., is
available on the official website of Python https://www.python.org.

Windows Installation

Here are the steps to install Python on Windows machine.

 Open a Web browser and go

to https://www.python.org/downloads/.

 Follow the link for the Windows installer python-XYZ.msifile where XYZ is the
version you need to install.

 To use this installer python-XYZ.msi, the Windows system must support Microsoft
Installer 2.0. Save the installer file to your local machine and then run it to find out if
your machine supports MSI.
  Run the downloaded file. This brings up the Python install wizard, which is really
easy to use. Just accept the default settings, wait until the install is finished, and you
are done.

The Python language has many similarities to Perl, C, and Java. However, there are some
definite differences between the languages.

First Python Program

Let us execute programs in different modes of programming.

Interactive Mode Programming

Invoking the interpreter without passing a script file as a parameter brings up the following
prompt −

$ python

Python2.4.3(#1,Nov112010,13:34:43)

[GCC 4.1.220080704(RedHat4.1.2-48)] on linux2

Type"help","copyright","credits"or"license"for more information.

>>>

Type the following text at the Python prompt and press the Enter −

>>>print"Hello, Python!"

If you are running new version of Python, then you would need to use print statement with
parenthesis as in print ("Hello, Python!");. However in Python version 2.4.3, this produces
the following result −
Hello, Python!
Script Mode Programming

Invoking the interpreter with a script parameter begins execution of the script and continues
until the script is finished. When the script is finished, the interpreter is no longer active.

Let us write a simple Python program in a script. Python files have extension .py. Type the
following source code in a test.py file −

print"Hello, Python!"

We assume that you have Python interpreter set in PATH variable. Now, try to run
this program as follows −

$ python test.py

This produces the following result −

Hello, Python!

Flask Framework:

Flask is a web application framework written in Python. Armin Ronacher, who leads
an international group of Python enthusiasts named Pocco, develops it. Flask is based on
Werkzeug WSGI toolkit and Jinja2 template engine. Both are Pocco projects.

Http protocol is the foundation of data communication in world wide web. Different
methods of data retrieval from specified URL are defined in this protocol.

The following table summarizes different http methods −

Sr.No Methods & Description

1 GET

Sends data in unencrypted form to the server. Most common method.

2 HEAD

Same as GET, but without response body

3 POST

Used to send HTML form data to server. Data received by POST method is not
cached by server.

4 PUT

Replaces all current representations of the target resource with the uploaded
content.

5 DELETE

Removes all current representations of the target resource given by a URL

By default, the Flask route responds to the GET requests. However, this preference can
be altered by providing methods argument to route() decorator.

In order to demonstrate the use of POST method in URL routing, first let us create an
HTML form and use the POST method to send form data to a URL.
Save the following script as login.html

<html>

<body>

<formaction="http://localhost:5000/login"method="post">

<p>Enter Name:</p>

<p><inputtype="text"name="nm"/></p>

<p><inputtype="submit"value="submit"/></p>

</form>

</body>

</html>

Now enter the following script in Python shell.

from flask importFlask, redirect,url_for,

request app=Flask(name )

@app.route('/success/<name>')

def success(name):

return'welcome %s'%

name

@app.route('/

login',methods=['POST','GET']) def

login():
user=request.form['nm']

return redirect(url_for('success',name=

user)) else:

user=request.args.get('nm')

return redirect(url_for('success',name=

user)) if name ==' main':

app.run(debug =True)

After the development server starts running, open login.html in the browser, enter name in
the text field and click Submit.

Form data is POSTed to the URL in action clause of form tag.

http://localhost/login is mapped to the login() function. Since the server has received data
by POST method, value of „nm‟ parameter obtained from the form data is obtained by −
user = request.form['nm']

It is passed to ‘/success’ URL as variable part. The browser displays

a welcome message in the window.

Change the method parameter to ‘GET’ in login.html and open it again in the browser. The
data received on server is by the GET method. The value of „nm‟ parameter is now
obtained by −

User = request.args.get(„nm‟)

Here, args is dictionary object containing a list of pairs of form

parameter and its corresponding value. The value corresponding to „nm‟ parameter is passed
on to „/success‟ URL as before.
What is Python?

Python is a popular programming language. It was created in 1991 by Guido van Rossum.
It is used for:

 web development (server-side),

 software development,

 mathematics,

 system scripting.

What can Python do?

 Python can be used on a server to create web applications.

 Python can be used alongside software to create workflows.

 Python can connect to database systems. It can also read and modify files.
 Python can be used to handle big data and perform complex mathematics.
 Python can be used for rapid prototyping, or for production-ready software
development.
Why Python?

 Python works on different platforms (Windows, Mac, Linux, Raspberry Pi, etc).
 Python has a simple syntax similar to the English language.

 Python has syntax that allows developers to write programs with fewer lines than
some other programming languages.
 Python runs on an interpreter system, meaning that code can be executed as soon as it
is written. This means that prototyping can be very quick.
  Python can be treated in a procedural way, an object-orientated way or a functional
way.
Good to know

 The most recent major version of Python is Python 3, which we shall be using in this
tutorial. However, Python 2, although not being updated with anything other than
security updates, is still quite popular.
 In this tutorial Python will be written in a text editor. It is possible to write Python in
an Integrated Development Environment, such as Thonny, Pycharm, Netbeans or
Eclipse which are particularly useful when managing larger collections of Python
files.
Python Syntax compared to other programming languages

 Python was designed to for readability, and has some similarities to the English
language with influence from mathematics.
 Python uses new lines to complete a command, as opposed to other programming
languages which often use semicolons or parentheses.
 Python relies on indentation, using whitespace, to define scope; such as the scope
of loops, functions and classes. Other programming languages often use curly-
brackets for this purpose.

Python Install

Many PCs and Macs will have python already installed.

To check if you have python installed on a Windows PC, search in the start bar for Python
or run the following on the Command Line (cmd.exe):

C:\Users\Your Name>python --version

To check if you have python installed on a Linux or Mac, then on linux open the command
line or on Mac open the Terminal and type:
python --version

If you find that you do not have python installed on your computer, then you can download
it for free from the following
website: https://www.python.org/

Python Quickstart

Python is an interpreted programming language, this means that as a developer you write
Python (.py) files in a text editor and then put those files into the python interpreter to be
executed.

The way to run a python file is like this on the command line: C:\Users\Your Name>python
helloworld.py
Where "helloworld.py" is the name of your python file.
Let's write our first Python file, called helloworld.py, which can be done in any text editor.

helloworld.py

print("Hello, World!")

Simple as that. Save your file. Open your command line, navigate to the directory where you
saved your file, and run:

C:\Users\Your Name>python helloworld.py

The output should read:
Hello, World!

Congratulations, you have written and executed your first Python program.
The Python Command Line
To test a short amount of code in python sometimes it is quickest and easiest not to write the
code in a file. This is made possible because Python can be run as a command line itself.

Type the following on the Windows, Mac or Linux command line: C:\Users\Your
Name>python
From there you can write any python, including our hello world example from earlier in the
tutorial:

C:\Users\Your Name>python
Python 3.6.4 (v3.6.4:d48eceb, Dec 19 2017, 06:04:45) [MSC
v.1900 32
bit (Intel)] on win32
Type "help", "copyright", "credits" or "license" for more
information.

Which will write "Hello, World!" in the command line:

C:\Users\Your Name>python
Python 3.6.4 (v3.6.4:d48eceb, Dec 19 2017, 06:04:45) [MSC
v.1900 32
bit (Intel)] on win32
Type "help", "copyright", "credits" or "license" for more
information.
>>> print("Hello,
Whenever you are done in the python command line, you can simply type the following to
quit the python command line interface:

exit()
Execute Python Syntax
As we learned in the previous page, Python syntax can be executed by

writing directly in the Command Line:

>>> print("Hello, World!")

Hello, World!
Or by creating a python file on the server, using the .py file extension, and running it in
the Command Line:
C:\Users\Your Name>python myfile.py
Python Indentations

Where in other programming languages the indentation in code is for readability only, in
Python the indentation is very important.
Python uses indentation to indicate a block of code.

Example if
5 > 2:
print("Five is greater than two!")

Python will give you an error if you skip the indentation:

Example if
5 > 2:
print("Five is greater than two!")

Comments

Python has commenting capability for the purpose of in-code

documentation.
Comments start with a #, and Python will render the rest of the line as a comment:
Example

Comments in Python:

#This is a comment.
print("Hello, World!")
Docstrings

Python also has extended documentation capability, called docstrings. Docstrings can be
one line, or multiline.
Python uses triple quotes at the beginning and end of the docstring: Example
Docstrings are also comments:
"""This is a

multiline docstring."""

print("Hello, World!")

3.6 SYSTEM REQUIREMENTS

HARDWARE REQUIREMENTS

 System : i5 Processor

 Hard Disk : 500 GB.

 Input Devices : Keyboard, Mouse

 Ram : 8GB.

SOFTWARE REQUIREMENTS

 Operating system : Windows

 Coding Language : Python

 IDE : Flask web app

3.7 ARCHITECTURE DIAGRAM
3.8 MODULES

 Collection of User‟s Reviews

 Pre-Processing

 Feature Selection
  Sentiment Word Identification

 Sentiment Polarity Identification

 Sentiment Classification

 Analysis of Reviews

Modules Description Collection of

User’s Reviews
Reviews are necessary for doing the Sentiment Analysis Task. For the Collection of
reviews there are different techniques which are used in this survey. The reviews can be a
structured, semi-structured and unstructured type. Sentiment Analysis research, there are
open source framework where researcher can get their data for the research purpose. R is one
of the programming language and software environment for statistical computing and
graphics supported by the R Foundation for Statistical Computing. By installing required
packages and authentication process of social website, to crawl the reviews from that site is
easy task. Once we have our text data with us then we can use that data for Pre-processing
purpose.

Pre-Processing

In pre-processing following are some tasks:

• Removing URLs, Special characters, Numbers, Punctuations etc.

• Removing Stop words

• Removal of Retweets (in case of twitter dataset)

• Stemming
• Tokenization

Feature Selection

Feature selection from pre-processed text is the difficult task in sentiment analysis.
The main goal of the feature selection is to decrease the dimensionality of the feature space
and thus computational cost. Feature selection will reduce the over fitting of the learning
scheme to the training data. In different machine learning algorithms were analysed on a
news review dataset with different feature selection techniques features are usually unigrams,
bigrams and grams. POS tagging is used in feature selection techniques.

Sentiment Word Identification

Sentiment word identification is a fundamental work in numerous applications of

sentiment analysis and opinion mining, such as review mining, opinion holder finding, and
review classification. Sentiment words can be classified into positive, negative and neutral
words.

Sentiment Polarity Identification

The basic task in SA is classifying the polarity of a given text at the document,
sentence, or feature. The polarity is in three category i.e. Positive, Negative and Neutral.
Polarity identification is done by using different lexicons which help to calculate sentiment
score, sentiment strength etc.

Sentiment Classification
 Sentiment classification of news review dataset and product review dataset is done
using supervised machine learning approaches like naïve Bayes, SVM, Maximum Entropy
etc. Accuracy is depends on which dataset is used for which classification methods. In the
case of Supervised machine learning approaches Training dataset is used to train the
classification model which then help to classify the test data.

Analysis of Reviews

Finally Analysis of result is important to make decision to individual and industry. In

case of news reviews if more result is positive then user can decide to go that news event.
Analysis is used in business intelligence.

3.9 ALGORITHMS:

Guiltlessness is an arranging cycle dependent on Base's hypothesis, which expects the

autonomy of theories. More or less, Naive Bayes records it as one of the classes that doesn't
has anything to do with different elements. The Vector Machine (SVM) support is an AI
calculation that can be utilized in stages and cycles. Notwithstanding, it is generally
expected utilized in arranging issues. In the SVM calculation, we configuration each item
as an article in the n-layered space (n is the quantity of resources it has), and the worth of
each item has a comparing esteem. We promptly look for and sort the hyper plane that
separates the two classes well overall.

1. Naïve bayes Algorithm:

P(X) due to an earlier case. The technique relies on split Bayes associated with the
conclusion of the first step on the assumption of free predictors. In the presence of the fixed
function of defined limits I am in the presence of a simple categorizer Bayes too much
foreign matter, and the other part of the bed. Even if it is the fruit of the well of the well - to
shine and the properties of each other's special occasions, a companion of the opposites of
one, or to confer the degree of his evil, whence it is said, `` which is good. Words for a Naive
Bayes is a simple example, so that significantly terribly useful, and huge sets for the sake
of knowledge. Simplicity is still attached to a more subtle kind of nice Bayes, the developer
thought.

Above,

• P (c | x) offered the prophets the last mechanical chance (c, objective) (x,
characteristic).
• P (c) is the main chance to watch out.
• P (x | c) is the capacity to anticipate the stage.

2. SVM Algorithm:

SVM upholds vector machines. For an informational index comprising of choices designed
on an introduced name, the A SVM records models that anticipate another example order.
Relegate other level/data displayed in classification 1. Assuming there are just two
classifications, it tends to be shown as a paired SVM list. Here are a few kinds of SVM:

• SVM line
• Lines without SVM lines
SVM Linear Classifier:
As far as enlistment, we will more often than not accept that the mentor gives a model at
home. These information focuses are planned to overcome any issues. Hyperplane forecast is
straightforwardly partitioned into two phases. The main thing to do when planning a
hyperplane is to diminish the separation from the hyperplane to the closest information in
two stages. The hyper-plane outline is displayed as the greatest hyper-plane.

SVM Non-Linear Classifier:

Our data bundles are broadly appropriated all over the planet. Getting this data from totally
various classes of hyperplants ought not be viewed as a decent choice. That is the reason
Vapnik recommended making a nonlinear classifier utilizing a hyper-plane stunt. In the
nonlinear SVM list, information focuses are relied upon to surpass the breaking point.

Examples of SVM boundaries:

In this section, we will figure out how to pick the best hyperplan to execute. We will show
you Category 2 data. The classes are displayed in triangles and circles.

Case 1:

• Take a gander at the issue in Figure 2 and the data in the two unique classes. Presently
we need to observe a decent hyper plane that can isolate the two classifications.
• For this situation, see Figure 1. on the option to see as the proper hyper plane In
SVM, we attempt to build the distance between the hyper-plane and the closest
information. This is known as an edge.
• Arrangement 1 is restricted, so it is more than the distance between the left and right
sides of the example. So, our most elevated hyperplan edge will be "first".
 • hyperplan edge will be "first".

Case 2:

• In Figure 2, we think about two distinct classes of media. Presently we need to find a
decent hyperplane that can separate between the two classes.
• Information for every class is circulated to the left or right. We will probably pick a
hyperplan that can separate between classes for most extreme contrasts.
• For this situation, the choice limits are ordered, yet the limits of choice 1 demonstrate
the most extreme distinction between \ bigtriangleup and \ bigcirc.
3.10 DATA FLOW DIAGRAM
ER DIAGRAMS
 UML DIAGRAM

USE CASE DIAGRAM

register\
login

importing data
sets
user
data
creating a chat
application base

sending the message through social

media

text segmentation word

score
SEQUENCE DIAGRAM

user analysis database

1: to the system()
register/login
sucessfully()
2:

3 : importing e datasets()
th

4 : storing the datasets()

5 : reterving datasets for

analysis()

6 : analysis
process()

7 : posting the short

8:
understanding()
COLLABRATION DIAGRAM
CHAPTER – IV

RESULT AND DISCUSSION

 CONCLUSION AND FUTURE WORK

CONCLUSION

The primary reason for this new proposed strategy is essential for the word, which was tried
utilizing six notable data control frameworks at Stanford. Obviously joining text, action
words, and action words has been great for consolidating various grammatical features. In
this undertaking, we utilized the Twitter API utilizing open- source devices R. The Twitter
account we have gathered is additionally an instrument for pre-handling. R utilizes
apparatuses to open message handling instruments and download data sent by means of web-
based media destinations like twitter and Facebook. The film survey was likewise set up in
the R examination and analysis materials. There are different controlled and uncontrolled
strategies, various word references, word references, and corpus-based techniques that are
extremely useful in enthusiastic examination. Different snippets of data can be utilized, for
example, film surveys, audit items, and Epinions news. This technique permits you to
ascertain the quantity of positive, negative and one-sided hashtags and to foresee general
assessment on what occurred. The above examination, directed on different #Hashtags of
feeling investigation, shows that industry individuals can get an overall thought of what
occurred.
FUTURE WORK
The subsequent stage in examining the item is to recognize the item in abundance, which can
assist clients with choosing to purchase the item online at the internet business website. The
responsiveness level examination gives definite data about the item or survey of the film,
so the producer should know about what the client knows in the film, perhaps with a film-
based investigation. Likewise with any film audit, the inn proprietor should realize what
individuals like in the inn and what different clients need
REFERENCES

[1] J. Serrano-Guerrero et al., “A google wave-based fuzzy recommender system to

disseminate information in University Digital Libraries 2.0,” Information Sciences, Vol.
181, no.9, pp. 1503- 1516, May. 2011.

[2] Z. Zhang et al., “A hybrid fuzzy-based personalized recommender system for telecom
products/services,” Information Sciences, Vol. 235, pp. 117-129, Jun. 2013

[3] Z.B. Sun et al., “Recommender systems based on social networks,” Journal of
Systems and Software,
Vol. 99, pp. 109-119, Jan. 2015

[4] X.L. Zheng et al., “A Hybrid Trust-Based Recommender System for Online
Communities of Practice,” IEEE Transactions on Learning Technologies, Vol. 8 no. 4,
pp. 345-356. Apr. 2015.

[5] L.O. Colombo-Mendoza et al., “RecomMetz: A context- aware

knowledge-based mobile recommender system for movie showtimes,” Expert
Systems with Applications, Vol. 42, no. 3, pp. 1202- 1222, Feb. 2015.

[6] Ji fang, Bi Chen, “Incorporating Lexicon Knowledge into SVM Learning to Improve
Sentiment Classification”, Proceedings of the Workshop on Sentiment Analysis where AI
meets Psychology (SAAIP), IJCNLP 2019

[7] Mika V. Mantyla, Daniel Graziotin and Miikka Kuutila, “The Evolution of Sentiment
Analysis-A Review of Research Topics”,
 Computer Science Review, Vol. 27, No. 1, pp. 16-32, 2018

[8] Muhammad Taimoor Khan, Mehr Durrani2, Armughan Ali, Irum Inayat, Shehzad
Khalid and Kamran Habib Khan “Sentiment analysis and the complex natural language”
Khan et al. Complex Adapt Syst Model (2016)

[9] Anvar Shathik,, Krishna Prasad Karani “A Literature Review on Application of

Sentiment Analysis Using Machine Learning Techniques” Aug 2020

[10] G.M.L. Sarne, “A novel hybrid approach improving effectiveness of recommender

systems,” Journal of Intelligent Information Systems, Vol. 44, no. 3, pp. 397-414, Jun.
2015.

[11] A. Tejeda-Lorente et al., “REFORE: A recommender system for researchers based on

bibliometrics,” Applied Soft Computing, Vol. 30, pp. 778-791, May 2015.

[11] Jessie Richie Naval de Los Santos “Depression among Public School Teachers in the
Philippines: A News Sentiment Analysis” Jan 2021

[12] B. Amini et al., “A reference ontology for profiling scholar's background knowledge
in recommender systems,” Expert Systems with Applications, Vol. 42, no. 2, pp. 913-928,
Feb. 2015.

[13] Understanding Sentiment Analysis: What It Is and Why It‟s Used Understanding
Sentiment Analysis: What It Is and Why It‟s Used, Available at:
https://www.brandwatch.com/blog/understanding- sentiment-analysis/
[14] Sentiment Analysis Explained, Available at:
https://www.lexalytics.com/technology/sentiment-analysis

[15] Hafiz Muhammad Ahmed, Mazhar Javed Awan, Faisal Shehzad “Sentiment
Analysis of Online Food Reviews using Big Data Analytics”

Apr 2021

APPENDIX

A.SAMPLE CODE:

from flask import Flask,render_template,url_for,request import pandas

as pd
import pickle

from sklearn.feature_extraction.text import CountVectorizer from

sklearn.naive_bayes import MultinomialNB
from sklearn.externals import joblib

app = Flask( name )

@app.route('/')

@app.route('/index') def
index():
return render_template('index.html')
@app.route('/login')
def login():

return render_template('login.html')
@app.route('/abstract') def
abstract():
return render_template('abstract.html')

@app.route('/future') def
future():
return render_template('future.html')
@app.route('/chart')
def chart():

return render_template('chart.html')
@app.route('/upload')
def upload():

return render_template('upload.html')
@app.route('/preview',methods=["POST"]) def
preview():
if request.method == 'POST':

dataset = request.files['datasetfile']

df = pd.read_csv(dataset,encoding = 'unicode_escape')
df.set_index('Id', inplace=True)
return render_template("preview.html",df_view = df)

@app.route('/home') def
home():
return render_template('home.html')

@app.route('/predict',methods=['POST'])
def predict():

df= pd.read_csv("D:/amazon.csv", encoding="latin-1")

# Features and Labels

df['LABEL']
df['REVIEW_TEXT']

X = df['REVIEW_TEXT'] y =
df['LABEL']

# Extract Feature With CountVectorizer cv =

CountVectorizer()
X = cv.fit_transform(X) # Fit the Data

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y,

test_size=0.33, random_state=42)

#Naive Bayes Classifier

from sklearn.naive_bayes import MultinomialNB

clf = MultinomialNB()
clf.fit(X_train,y_train)
clf.score(X_test,y_test) #Alternative Usage
of Saved Model
# joblib.dump(clf, 'NB_spam_model.pkl')

# NB_spam_model = open('NB_spam_model.pkl','rb') # clf =

joblib.load(NB_spam_model)
 if request.method == 'POST':

message = request.form['message'] data =

[message]
vect = cv.transform(data).toarray()
prediction = clf.predict(vect)
if prediction[0] == " label1 ":
label="extremist"
elif prediction[0] == " label2 ":
label="moderate"
return render_template('home.html',prediction = label)
@app.route('/chart1')
def chart1():

return render_template('chart1.html')
@app.route('/uploads')
def uploads():

return render_template('uploads.html')
@app.route('/previews',methods=["POST"]) def
previews():
if request.method == 'POST':

dataset = request.files['datasetfile']

df = pd.read_csv(dataset,encoding = 'unicode_escape')
df.set_index('Id', inplace=True)
return render_template("previews.html",df_view = df)
@app.route('/chart2')
def chart2():

return render_template('chart2.html')
if name == ' main ':
app.run(debug=True)
B.SCREENSHOTS:
PLAGIARISM REPORT

i
ii
v