Project documentaion sample.docx

i
Tribhuvan University
Faculty of Humanities and Social Sciences
PROJECT REPORT ON
EYWRY (social media)
Submitted to
Department of Computer Application
DAV College
In partial fulfilment of the requirements for the Bachelors in
Computer Application
Submitted by
Hridam Dhimal [6-2-469-121-2018]
Priyanka Sharma [6-2-469-125-2018]
6th semester, 3rd year
Under the Supervision of
Er. Rishabh Jha

i
DAV College
Supervisor’s Recommendation
I hereby recommend that this project prepared under my supervision by HRIDAM
DHIMAL AND PRIYANKA SHARMA entitled “Eywry” in partial fulfillment of the
requirements for the degree of Bachelor of Computer Application is recommended for the
final evaluation
.
……………………………..
SIGNATURE
Er. Rishabh Jha
SUPERVISOR
Lecturer
Faculty of humanities and science
DAV College

ii
DAV College
LETTER OF APPROVAL
This is to certify that this project prepared by HRIDAM DHIMAL AND PRIYANKA
SHARMA entitled “Eywry” in partial fulfillment of the requirements for the degree of
Bachelor in Computer Application has been evaluated. In our opinion it is satisfactory in
the scope and quality as a project for the required degree.
_________________________
Signature
Er. Rishabh Jha
Lecturer
DAV College
Dhobighat, Lalitpur
_________________________
Signature
Er. Sudip Adhikari
HOD
DAV College
Dhobighat, Lalitpur
_________________________
Signature
Internal Examiner:
_________________________
Signature
External Examiner:

iii
ACKNOWLEDGMENT
In the accomplishment of this project successfully, many people have best owned upon
their blessing and the heart pleased support, this time we are utilizing to thank all the people
who have been concerned with this project.
We will like to extend our sincere thanks to Tribhuvan University for giving us the golden
opportunity in enhancing our hidden capabilities. Our next thanks will be given to the DAV
College whose helps us by giving the perfect environment for learning and for proper
infrastructure. The list also includes the Co-Ordinator of Bachelor Department, Mr. Sashi
Bhusan Chaturvadi, And, also to our Head of Department Mr. Sudip Adhikari
Unfortunately, we address several difficulties in coordinating the activities of the project
but we are highly indebted to Mr. Rishabh Jha for his guidance and constant supervision,
as well as the providing necessary information regarding the project and also for his support
in completing the project.
Last but not least we would like to thank to my classmates who helped us a lot to support
us during making of this project.
With Regards
Hridam Dhimal
TU Registration No: 6-2-469-121-2018
Priyanka Sharma
TU Registration No: 6-2-469-125-2018

iv
ABSTRACT
The aim of this project is to deploy and develop positivity towards people using the social
media. Nowadays, many social media have been spreading the negativity thoughts and
negative content towards people so to stop from the negativity things we have developed
“Eywry” (social media) web-based application in which it helps to only share the positivity
content towards people.
In this web-based application only the positive content is taken from the user if there is any
negative content then user will not be able to post the content or the negative content will
be deleted from the database. So, to complete this project we have used a spiral
Methodology because we have to take feedback from the customer to make it more reliable
to the user. So, this project aim is only been completed by using the Sentiment analysis
which is the main key element of the project. The Sentiment analysis is act of recognizing
and categorizing opinion contained in a piece of text, especially in order to recognize
whether the writer has a positive, negative, or neutral attitude towards a given topic,
product etc. So, to declare the text is positive or negative we need to first train the data in
other word called the Supervised Learning. The data is extracted from the data source
“Kaggle” that has collected the data from google play store reviews. While has data up to
875 data. In which the 80% data to train and 20% to test the data. While training and testing
the data, the system gave the accuracy level of 82% which is great for the analyzing the
text. The technologies used are: Python, Supervised Learning, and Data Visualization
Skills. The sentiment analysis not only helps to determine the positive, negative or neutral
sentiments but also helps in real time analysis, sorting data at a scale. While doing this
project we have Learned different new thing that we are never familiar with so it was a
wonder experience as well as excitement doing this project. There are still some bugs and
error that may appear in the project so the solving process will be going on as well the
training data will also be update according the user posts.

v
Table of Contents
ACKNOWLEDGMENT.....................................................................................................iii
ABSTRACT........................................................................................................................iv
TABLE OF FIGURES .......................................................................................................vii
LIST OF TABLES............................................................................................................ viii
CHAPTER 1 ....................................................................................................................... 1
INTRODUCTION .............................................................................................................. 1
1.1 INTRODUCTION .................................................................................................... 1
1.2 PROBLEM STATEMENT....................................................................................... 2
1.3 OBJECTIVES ........................................................................................................... 2
1.4 SCOPE AND LIMITATION.................................................................................... 2
1.5 DEVELOPMENT METHODOLOGY..................................................................... 3
1.6 REPORT ORGANIZATION.................................................................................... 4
CHAPTER 2 ....................................................................................................................... 5
BACKGROUND STUDIES AND LITERATURE REVIEW ........................................... 5
2.1 BACKGROUND STUDIES ..................................................................................... 5
2.2 LITERATURE REVIEW ......................................................................................... 5
2.2.1 Twitter................................................................................................................ 5
2.2.2 Restaurant and hotel data ................................................................................... 6
2.2.3 Movie Review.................................................................................................... 6
2.3.4 Yik Yak.............................................................................................................. 6
CHAPTER 3 ....................................................................................................................... 7
SYSTEM ANALYSIS AND DESIGN............................................................................... 7
3.1 SYSTEM ANALYSIS .............................................................................................. 7
3.1.1 Requirement and Analysis. ................................................................................ 7
3.1.2 Feasibility Analysis............................................................................................ 9
3.1.3 Object Modeling: Class and Object Diagram .................................................. 10
3.1.4 Dynamic Modeling: Sequence Diagram.......................................................... 12
3.1.5 Process Modeling: Activity Diagram............................................................... 13
3.2 SYSTEM DESIGN ................................................................................................. 15
3.2.1 Component Diagram........................................................................................ 15

vi
3.2.2 Deployment diagram........................................................................................ 16
3.3 ALGORITHM DETAILS ....................................................................................... 17
3.3.1 Introduction of Naive Bayes Classifier:........................................................... 17
3.3.2 How Naive Bayes Work: ................................................................................. 17
3.3.3 Application of Naive Bayes:............................................................................ 18
3.3.4 Data training:.................................................................................................... 18
CHAPTER 4 ..................................................................................................................... 21
IMPLEMENTATION AND TESTING ........................................................................... 21
4.1 IMPLEMENTATION............................................................................................. 21
4.1.1 Tools Used: ...................................................................................................... 21
4.1.2 Implementation details of modules:................................................................. 25
4.2 TESTING................................................................................................................ 29
4.2.1 Purpose of Testing: .......................................................................................... 29
4.2.2 Test case for Unit Testing:............................................................................... 29
4.2.3 Test case for System Testing: .......................................................................... 45
CHAPTER 5 ..................................................................................................................... 46
CONCLUSION AND RECOMMENDATIONS ............................................................. 46
5.1 CONCLUSION....................................................................................................... 46
5.2 LESSON LEARNT/OUTCOME............................................................................ 46
5.3 FUTURE RECOMMENDATIONS ....................................................................... 46
References......................................................................................................................... 47

vii
TABLE OF FIGURES
Figure 1: Spiral Model.........................................................................................................4
Figure 2: Use Case Diagram (a) of the System....................................................................7
Figure 3 :Use Case Diagram (b) of the System ...................................................................8
Figure 4: Class Diagram of the System .............................................................................11
Figure 5: Object Diagram of the System ...........................................................................12
Figure 6: Sequence Diagram of the System.......................................................................13
Figure 7: Process Modeling of the System ........................................................................14
Figure 8: Component Diagram ..........................................................................................15
Figure 9: Deployment Diagram of the System ..................................................................16
Figure 10: Data Training Table..........................................................................................19
Figure 11: Training and Validation Accuracy ...................................................................20
Figure 12: Data Trained .....................................................Error! Bookmark not defined.
Figure 13: Token Analysis Module ...................................................................................28
Figure 14: Sign Up of the Page..........................................................................................30
Figure 15: Login Form Page of the System.......................................................................30
Figure 16: Login by User...................................................................................................31
Figure 17: User Page After Login into the System............................................................32
Figure 18: Posting the only positive Content (a) ...............................................................33
Figure 19: Posting the only positive Content (b) ...............................................................33
Figure 20: User Page..........................................................................................................34
Figure 21:Post Page of the System ....................................................................................35
Figure 22: Delete Post (a) ..................................................................................................36
Figure 23: Delete Post (b) ..................................................................................................37
Figure 24: Edit Post (a) ......................................................................................................38
Figure 25 :Edit Pos (b)t......................................................................................................38
Figure 26: Edit Post (c) ......................................................................................................39
Figure 27: Edit Username (a).............................................................................................40
Figure 28: Edit Username (b).............................................................................................40
Figure 29: Edit Post page...................................................................................................41
Figure 30: Edit Detail Post.................................................................................................41
Figure 31: Successfully Edited ..........................................................................................42
Figure 32: About System ...................................................................................................43
Figure 33: Logout Page of the System...............................................................................44
Figure 34: Back to Login Page after Logout .....................................................................44
Figure 35: Gantt Chart……………………………………………………………………14

viii
LIST OF TABLES
A) Signup page:...............................................................................................................29
B) Login Page: ................................................................................................................31
C) Posting only the positive Content: .............................................................................32
D) User Page: ..................................................................................................................34
E) Post Page:...................................................................................................................35
F) Delete Post: ................................................................................................................36
G) Edit Post:....................................................................................................................37
H) Edit User Name, Email and Password:......................................................................39
I) About page:................................................................................................................42
J) Logout:.......................................................................................................................43

1
CHAPTER 1
INTRODUCTION
1.1 INTRODUCTION
Since, the Internet has rapidly grown in the past few years and more and more daily tasks
and operations are done online using different computer and handheld devices. One of
which is seeing the online post in a social media and sharing the personal thing in the social
media.
There are many social media applications like Facebook, Twitter, Instagram, and many
more. The most common thing among these applications is the platform where you can
post anything you like revealing who the user is and what their interests are. It may either
be the positive or the negative post. And might result in larger impact on the society, be it
be a positive or negative impact. Social media refers to a computer-based technology that
facilitates the sharing of ideas, thoughts, and information through virtual networks and
communities. Social media is internet-based and gives users quick electronic
communication of content, such as personal information, documents, videos, and photos.
Users engaged with social media via a computer, tablets, or smartphones via web-based
software or applications. While social media is ubiquitous in America and Europe, Asian
countries like Indonesia lead the list of social media usage. Nepal has seen its own usage
of social media up on larger scale than ever in the history, the rapid usage growth only
seems to be increasing. Social media takes many forms of varieties of tech-enabled
activities. These activities include photo sharing, blogging, social gaming, social networks,
video shearing, business networks, virtual worlds, reviews, and much more. Even
governments and politicians utilize social media to engage with constituents and voters. It
is considered one of the most important gateways for the people of the nation to get their
hands on the events of the world and nation. Companies all around the globe focuses more
on their social growth through social media, as it can be seen with large social following
in these platforms can mean the companies are doing well and good. 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.

2
1.2 PROBLEM STATEMENT
Social media has been an inseparable part of everyone’s life. Our sentiments are poured
into the posts in which we get engaged. These posts and comments play a very big role in
the mental health of users. Nowadays the toxicity in social media is affecting the quality
of these platforms. It is seen that the social media post spilling negativities will impact very
seriously to everyone who has come across the post. Similarly, users don’t want to reveal
identity for speaking for some serious issues where revealing identity can be a threat for
the user. Anonymous user identity for the posts related to social and other thought-
provoking issues is needed in the social media sites for a safer environment creation.
Some of the problem statement by using the social media are listed below:
1. Negative Post
2. Cyberbullying
3. Cyberstalk
4. Self-absorption
1.3 OBJECTIVES
The project is bases on the following objectives:
1. To make the web application community for the positivity.
2. To make the application community for the privacy concern.
1.4 SCOPE AND LIMITATION
The project has got some of the following scopes:
1. A safe environment can be created in social media which preserves the identity of
the users.
2. Toxicity in social media can be checked so that a healthy environment can be
created for all the users.
3. Anonymous user posting can be implemented so that freedom of speech and
expression can be preserved.
4. A safer social networking site for all can be created.
5. Hate crime, hatred, manipulated views/news can be fragged off directly creating a
safe and user-friendly social media site.

3
The project has got some of the following limitation:
1. Post authentication cannot be proved to the viewers, that is, the user won’t know
who has posted.
2. The accuracy of flagging off the post is low due to the lack of training data.
However, it will increase over time.
3. False claims having positive polarity cannot be flagged off as of now.
1.5 DEVELOPMENT METHODOLOGY
For the development methodology we have used the spiral model in which it is a system
development life cycle model utilized when the project managers are working on a software
project. By using this methodology, we can get the customer satisfaction which is not sure
about the needs in the web application or the project, so our project aim is to serve the best
services to the user according to the user feedback throughout the process. We have made
different changes and adjustments using this methodology which help to keep the project
at low risk and less error. It also helps to make the development work easy as while working
we can add the next user requirement as all the phases have completed and still adding
more on the project.
In the Spiral model approach, the whole process of software development is divided into
separate phases. The outcome of one phase acts as the input for the next phase sequentially.
The spiral model passes through four phases over and over in a “spiral” until completely.
The four phases are: Identification, Design, Construct or Build and lastly, Evaluation and
Risk Analysis.

4
Figure 1: Spiral Model
1.6 REPORT ORGANIZATION
This project report has been organized into various chapters:
The First Chapter discusses the overall project introduction. This chapter includes the
project's introduction, problem statement, objectives, scope and limitation and
Development methodology has been included.
The Second Chapter of this project report has discussed the Background Study and
Literature Reviews.
The Third Chapter is the main focused chapter among all the chapter where it shows the
System analysis and design where it includes the functional and non-functional
requirements, feasibility analysis, object and class diagram, state and sequence diagram,
Activity Diagram, refinement of classes and object, component and deployment diagram
and lastly the main important part the algorithm used in the project.
The Fourth Chapter explains about the implementation aspect of the project, and testing
the system using the different screen shots of various modules.
The Final Chapter discusses the conclusion of the project, the lesson learnt and the future
recommendation.

5
CHAPTER 2
BACKGROUND STUDIES AND LITERATURE REVIEW
2.1 BACKGROUND STUDIES
Sentimental analysis involves investigating the approach of a writer towards a particular
subject or the overall contextual polarity of an entire document. The underlying purpose of
sentimental analysis is to classify the text based on sentiment or opinion, not by topics, in
particular, sentiment analysis incorporates the user of information retrieval, NLP, data
mining, and knowledge management techniques for identifying and extracting subjective
information for a large volume of unstructured data [1]. As per, sentiment analysis is a
complex process that includes five phases for analyzing the sentiment in the source
materials. These phases include the collection of data, preparation of text, detection of
sentiment, classification of sentiment, and presentation of findings.
In the age of social media, a single viral review can burn down an entire brand. On the
other hand, research by Bain & Co. shows that good experiences can grow 4-8% revenue
over competition by increasing customer lifecycle 6-14x and improving retention up to
55% [2].
The sentiment analysis technique is applied mainly in two approaches: supervised learning
and unsupervised learning. The supervised learning approach involves sorting the training
set to create text-based patterns. The unsupervised learning approach does now involve the
user of a database but rather is based on the set of words where the terms negative and
positive are considered. Therefore, the frequency in terms of the negative and positive in
the entire text provides an indication for tagging the document based on the terms.
Sentiment analysis is used in several diverse fields.
2.2 LITERATURE REVIEW
2.2.1 Twitter
In 2019, Saad and Yang have aimed for giving a complete tweet sentiment analysis on the
basis of ordinal regression with machine learning algorithms. The suggested model
included preprocessing tweets as the first step and with the feature extraction model, an
effective feature was generated. The methods such as SVR, RF, Multinomial logistic

6
regression (SoftMax), and DTs were employed for classifying the sentiment analysis.
Moreover, twitter dataset was used for experimenting with the suggested model. The test
results have shown that the suggested model has attained the best accuracy, and also DTs
were performed well when compared over other methods. [3] [4]
2.2.2 Restaurant and hotel data
In 2019, Afzaal recommended a novel approach of aspect-based sentiment classification,
which recognized the features in a precise manner and attained the best classification
accuracy. Moreover, the scheme was developed as a mobile application, which assisted the
tourists in identifying the best hotel in the town, and the proposed model was analyzed
using the real-world data sets. The results have shown that the presented model was
effective in both recognition as well as classification. [5]
2.2.3 Movie Review
In 2019, Abdi suggested a deep-learning-based technique for categorizing the opinion of
the user mentioned in reviews. Moreover, a deep learning model was a unified feature set
that was representative of sentiment shifter rules, word embedding, sentiment knowledge,
linguistic and statistical knowledge has not been continuously explored for a sentiment
analysis. Moreover, the suggested model used RNN that consisted of LSTM for
considering the benefit of sequential processing and conquered many issues in
conventional algorithms. [6]
2.3.4 Yik Yak
In 2013, Yik Yak swept the nation as it became popular across college campuses as well
as in middle and high school. Yik Yak is an anonymous, controversial social media
application that allows people to make posts that are visible to other users within ~2 miles.
Due to the anonymous nature of the app, users often post private, personal (or just plain
stupid) thoughts that they would never reveal to offline friends. The app bills itself as a
place to "share your thoughts with people around you while keeping your privacy." It
should be evident that the company must take necessary precautions to prevent users' posts
from being exposed by a malicious attacker. [7]

7
CHAPTER 3
SYSTEM ANALYSIS AND DESIGN
3.1 SYSTEM ANALYSIS
It is a process of observing systems for troubleshooting or developing purposes. It is an
approach to information technology, where computer-based systems require defined
analysis according to their makeup and design.
3.1.1 Requirement and Analysis.
There are many requirements of the system which should be analyzed so that effective
output can be produced with available resources.
I. Functional Requirement.
The functional requirement indicates what a software system must do and
how it must function. In our project, we have made a social media where
sentiment analysis takes place by the Data abstraction, Data visualization,
Data tokenization, Data analysis. The functional requirement can be more
understood by the following user case diagram.
Figure 2: Use Case Diagram (a) of the System

8
Figure 3 :Use Case Diagram (b) of the System
II. Non-Functional Requirement.
Non-Functional will describe how a system should behave and what limits
there are on its functionally. The Non-Functional requirements cover all the
remaining requirements which are not covered by the functional
requirements. The Non-Functional requirements of the system are given
below:
CATEGORY Non-Functional Requirement
Usability The user will find it very easy for the programmer but difficult for the
user who is not computer literate.
Reliability The system should perform its process in an accurate way and precision
to avoid problems and no data losses.
Performance The system runs smooth and fast relying on the hardware bases of
computers.
Implementation It can be implemented on the specific computer which supports it.
Speed and
Responsiveness
The system speed and responsiveness all depends upon the hardware of
the computer.

9
3.1.2 Feasibility Analysis.
Feasibility study includes consideration of all the possible ways to provide a solution to a
problem. That proposed solution should satisfy all the user requirements and should be
flexible enough so that future changes can be easily done based on the future upcoming
requirements.
● Economic Feasibility.
This is a very important aspect to be considered while developing a project. We
decided the technology based on the minimum possible cost factors.
- To use this web application, it doesn't require any cost.
- Overall, we have estimates that benefits the organization is going to receive
from the proposed system will surely overcome the initial cost and the later
on running cost for the system.
● Technical Feasibility.
This includes the study of function, performance and constraints that may affect the
ability to achieve an acceptable system. For this feasibility study, we studied
complete functionality to be provided in the system and checked if everything was
possible using different types of front-end and backend platform.
● Operational Feasibility.
This project is fully GUI (Graphical User Interface) based and is very user friendly
and all input to be taken are all self-explanatory even to a layman. Besides, proper
training has been conducted to let the user know the essence of the system. As far
as our study is concerned the clients are comfortable and happy as the system has
cut down their loads and doings.
● Gantt chart
A Gantt chart is a project management tool that illustrates a project plan. It typically
includes two sections: the left side outlines a list of tasks, while the right side has a
timeline with schedule bars that visualize work. The Gantt chart can also include

10
the start and end dates of tasks, milestones, dependencies between tasks, and
assignees.
Figure 35: Gantt Chart
3.1.3 Object Modeling: Class and Object Diagram
Object Modeling Technique (OMT) is a real world-based modeling approach for software
modeling and designing. It was developed basically as a method to develop object-oriented
systems and to support object-oriented programming. It describes the static structure of the
system.
- Class Diagram:
Class diagram is a static diagram. It represents the static view of an application.
Class diagram is not only used for visualizing, describing, and documenting
different aspects of a system but also for constructing executable code of the
software application. The purpose of class diagram is to model the static view of an
application. Class diagrams are the only diagrams which can be directly mapped
with object-oriented languages and thus widely used at the time of construction.

11
Figure 4: Class Diagram of the System
- Object Diagram:
An object diagram is similar to a class diagram except it shows the instances of
classes in the system. We depict actual classifiers and their relationships making
the use of class diagrams. On the other hand, an Object Diagram represents specific
instances of classes and relationships between them at a point of time.
Objects are the real-world entities whose behavior is defined by the classes. Objects
are used to represent the static view of an object-oriented system. We cannot define
an object without its class. Object and class diagrams are somewhat similar.

12
Figure 5: Object Diagram of the System
3.1.4 Dynamic Modeling: Sequence Diagram
Sequence diagrams, commonly used by developers, model the interactions between objects
in a single use case. They illustrate how the different parts of a system interact with each
other to carry out a function, and the order in which the interactions occur when a particular
use case is executed.
A sequence diagram is structured in such a way that it represents a timeline which begins
at the top and descends gradually to mark the sequence of interactions. Each object has a
column and the messages exchanged between them are represented by arrows.
In a sequence diagram it is necessary to identify the objects or actors that would be involved
in creating a new user account. Once the object is being identified, then it is important to
write a detailed description on what the use case does.

13
Figure 6: Sequence Diagram of the System
3.1.5 Process Modeling: Activity Diagram
Process modeling involves graphically representing the processes, or actions, that capture,
manipulate, store, and distribute data between a system and its environment and among
components within a system.
Activity diagram is another important diagram in UML to describe the dynamic aspects of
the system. Activity diagram is basically a flowchart to represent the flow from one activity
to another activity. The activity can be described as an operation of the system. Activity is
a particular operation of the system. Activity diagrams are not only used for visualizing the
dynamic nature of a system, but they are also used to construct the executable system by
using forward and reverse engineering techniques.

14
Figure 7: Process Modeling of the System
The above diagram shows how the user system works in the project. First the user has to
register the data and after that the user is taken to the login page where the user has to enter
the same data that has been entered while registering the data and it checks from the
database where the entered data is matched or not. If matched then it goes to the home
page, if not matched then it again goes to the user login page. After the successful login
the user is taken to the homepage with multiple options and views. The option to post the
content, edit the posted content and delete the posted content. And also, provide the access
to change the email, password and username of the login users. At last, the user can also
logout if the application is used.

15
3.2 SYSTEM DESIGN
System design is the process of defining the elements of a system such as the architecture,
modules and components, the different interfaces of those components and the data that
goes through that system. It is meant to satisfy specific needs and requirements of a
business or organization through the engineering of a coherent and well-running system.
3.2.1 Component Diagram.
The component diagram's main purpose is to show the structural relationships between the
components of a system. Component diagrams offer architects a natural format to begin
modeling a solution. Component diagrams allow an architect to verify that a system's
required functionality is being implemented by components, thus ensuring that the eventual
system will be acceptable. A component diagram breaks down the actual system under
development into various high levels of functionality. Each component is responsible for
one clear aim within the entire system and only interacts with other essential elements on
a need-to-know basis.
Figure 8: Component Diagram

16
3.2.2 Deployment diagram.
The deployment diagram visualizes the physical hardware on which the software will be
deployed. It portrays the static deployment view of a system. It involves the nodes and their
relationships. It ascertains how software is deployed on the hardware. It maps the software
architecture created in design to the physical system architecture, where the software will
be executed as a node. Since it involves many nodes, the relationship is shown by utilizing
communication paths.
The main purpose of the deployment diagram is to represent how software is installed on
the hardware component. It depicts in what manner a software interacts with hardware to
perform its execution. Both the deployment diagram and the component diagram are
closely interrelated to each other as they focus on software and hardware components. The
component diagram represents the components of a system, whereas the deployment
diagram describes how they are actually deployed on the hardware.
Figure 9: Deployment Diagram of the System

17
3.3 ALGORITHM DETAILS
3.3.1 Introduction of Naive Bayes Classifier:
Assume you wish to categorize users as good or bad. Sentiment Analysis is a popular job
to be performed by data scientists. This is a simple guide using Naive Bayes Classifier and
Scikit-learn to create a Google Play stores classifier (Sentiment Analysis) in Pythons. [8]
Naive Bayes is the simplest and fastest classification algorithm for a large chunk of data.
In various applications such as spam filtering, text classification, sentiment analysis, and
recommendation systems, Naive Bayes classifier is used successfully. It used the Bayes
probability theorem for unknown class prediction. [9]
The Naive Bayes classification techniques are simple and powerful classification tasks in
machine learning. The use of Bayes theorem with a strong independence assumption
between the features is the basis for naive Bayes classification When used for textual data
analysis, such as Natural Language Processing, the Naive Bayes classification yields good
results.
Simple Bayes or independent Bayes models are other names for Naive Bayes models. All
of these terms refer to the classifier’s decision rule using Bayes theorem. In practice, the
Bayes theorem is applied by the Naive Bayes classifier. The power of Bayes theorem is
brought to machine learning with these classifiers. [8]
3.3.2 How Naive Bayes Work:
The Bayes theorem is used by the Naive Bayes classifier to forecast membership
probabilities for each class, such as the likelihood that a given record or data point belongs
to the class, such as the likelihood that a given record or data point belongs to the class.
The most likely class is defined as the one having the highest probability. The Maximum
A posteriori is another for this (MAP).
For a hypothesis with two occurrences A and B, the MAP is
MAP (A)
=max(P(A|B))
=max(P(B|A)*P(A)/pP(B))
=max(P(B|A)-P(A))

18
P(B) stands for probability of evidence. It’s utilization to make the outcome more normal.
It had no effect on the outcome if it was removed. All of the features in the Naive Bayes
Classifier are assumed to be unrelated. A feature’s presence or absence has no bearing on
the presence or absence of other features.
This algorithm gives different evidence on features in real-world dataset. As a result, the
computations become fairly difficult. To make things easier, the feature independence
techniques are utilized to decouple various pieces of evidence and consider them as
separate entities. [10] [11]
3.3.3 Application of Naive Bayes:
Naive Bayes is one of the most straightforward and fast classification algorithms. It is very
well suited for large volumes of data. It is successfully used in various application such as:
- Spam Filtering
- Text Classification
- Sentiment Analysis
- Recommender System
It uses the bayes theorem of probability for the prediction of unknown classes.
3.3.4 Data training:
Here the data is being trained according to the google play store apps reviews where the
review is collected and stored to the data where the data will be calculated by their review
polarity. Where the polarity is 1 or 0. So the 1 defines the positivity and the 0 is defined as
the negative reviews. The data has been taken from the Kaggle webpage when the number
of data is 892. So, the data is trained according to the following data set shown in the figure:

19
Figure 10: Data Training Table
Show the data has been trained using the python using different packages named pandas,
NumPy, matplotlib where it helps to train the data. The output of the data train is up to 82%
accuracy means the post the user input is being all taken according to the training data. And
helps to post in the web application Eywry. The below Diagram shows the accuracy of the
dataset trained:

20
Figure 11: Training and Validation Accuracy

21
CHAPTER 4
IMPLEMENTATION AND TESTING
4.1 IMPLEMENTATION
4.1.1 Tools Used:
Different tools, applications and technologies have been used in this project. And all of
them are discussed below:
● Microsoft Visual Studio:
Microsoft Visual Studio is an Integrated Development Environment (IDE)
developed by Microsoft to develop GUI (Graphical user interface), console, web
application, web apps, mobile apps, cloud, and web server, etc. With the help of
this IDE, you can create manage a code as well as native code. It uses the various
platforms of Microsoft Software development software like windows store,
Microsoft Silverlight, and Windows API, etc. It is not a language-specific IDE as
you can use this to write code in c#, c++, VB (Visual Basic), Python, JavaScript,
and many more languages. It provides support for 36 different programming
languages.
● PostgreSQL:
PostgreSQL is an open-source, object-relational database management system
(ORDBMS) that is not owned or controlled by one company or individual. Because
PostgreSQL software is open-source, it is managed mostly through a coordinated
online effort by an active global community of developers, enthusiasts and other
volunteers.
PostgreSQL supports almost all relational database features and offers a few
unusual features that are normally absent in other RDBMS engines. Commonly
supported objects include views, stored procedures, indexes, triggers and object-
defined data types, in addition to general RDBMS features such as primary keys,
foreign key relationships and atomicity. [12]

22
● Frontend:
As a web developer, the three main languages we use to build websites are HTML,
CSS, and JavaScript. JavaScript is the programming language, we use HTML to
structure the site, and we use CSS to design and layout the web page.
- Html
HTML stands for Hyper Text Markup Language. It is a relatively simple
language that allows developers to create the basic structure of a website.
Even the most complex websites have HTML at their core. It’s also the
second-most-used programming language by developers.
HTML uses “elements,” or tags, to denote things like the beginning of a
paragraph, the bolding of a font, or the addition of a photo caption. In this
way, it controls how a webpage looks, how the text is separated and
formatted, and what the user sees. [13]
- CSS
If HTML represents the building blocks of a website, CSS is a way to shape
and enhance those blocks. CSS is a style sheet language used to specify the
way different parts of a webpage appear to users. In other words, it’s a way
to add some style and additional formatting to what you’ve already built
with HTML.
For example, perhaps you’ve used HTML to add header text, and now you
want that header to have a more pleasant font, a background color, or other
formatting elements that make it more sleek, professional, and stylish.
That’s where CSS comes in. CSS also helps websites adapt to different
device types and screen sizes so that your pages render equally well on
smartphones, tablets, or desktop computers. [13]
- JavaScript
JavaScript is a light-weight object-oriented programming language which
is used by several websites for scripting the webpages. It is an interpreted,

23
full-fledged programming language that enables dynamic interactivity on
websites when applied to an HTML document. With JavaScript, users can
build modern web applications to interact directly without reloading the
page every time. The traditional website uses JS to provide several forms of
interactivity and simplicity. In addition to web browsers, databases such as
CouchDB and MongoDB uses JavaScript as their scripting and query
language. [13]
- Bootstrap
Bootstrap is the most popular HTML, CSS and JavaScript framework for
developing a responsive and mobile friendly website. It is absolutely free to
download and use. It is a front-end framework used for easier and faster
web development. It includes HTML and CSS based design templates for
typography, forms, buttons, tables, navigation, modals, image carousels and
many others. It can also use JavaScript plug-ins. It facilitates you to create
responsive designs.
● Backend:
- Python
In technical terms, Python is an object-oriented, high-level programming
language with integrated dynamic semantics primarily for web and app
development. It is extremely attractive in the field of Rapid Application
Development because it offers dynamic typing and dynamic binding
options [14]
- To check whether software is built. It is as per the requirement or
not.
- Finding defects from the software before customers find them out.
- Defects get a fix from the developer.
- Preventing defects.
- Gaining confidence about the level of quality.

24
- Flask
Flask is an API of Python that allows us to build up web-applications. It
was developed by Armin Ronacher. Flask’s framework is more explicit than
Django’s framework and is also easier to learn because it has less base code
to implement a simple web-Application. A Web-Application Framework or
Web Framework is the collection of modules and libraries that helps the
developer to write applications without writing the low-level codes such as
protocols, thread management, etc. Flask is based on the WSGI (Web
Server Gateway Interface) toolkit and Jinja2 template engine. [14]
- Pandas
Pandas is a software library written for the Python programming language
for data manipulation and analysis. In particular, it offers data structures and
operations for manipulating numerical tables and time series. Data Frame
object for data manipulation with integrated indexing. Tools for reading and
writing data between in-memory data structures and different file formats.
Pandas is mainly used for data analysis. Pandas allows importing data from
various file formats such as comma-separated value, JSON, SQL database
tables or queries, and Microsoft Excel. Pandas allow various data
manipulation operations such as merging, reshaping, selecting, as well as
data cleaning, and data wrangling features. [14]
- Matplotlib
Matplotlib is a plotting library for the Python programming language and
its numerical mathematics extension NumPy. It provides an object-oriented
API for embedding plots into applications. Pyplot is a Matplotlib module
which provides a MATLAB-like interface.
Matplotlib is designed to be as usable as MATLAB with the ability to use
Python and the advantage of being free and open source. [14]

25
- Neattext
Neattext is a simple natural language processing package used for cleaning
the data. It can be used to clean sentences, extract emails, phone numbers,
emojis from sentences. Problem neattext is intended to solve: Cleaning of
unstructured text data. Reduce noise [special characters, stop words.
Reducing repetition of using the same code for text preprocessing. [14]
- NumPy
NumPy is a library for the Python programming language, adding support
for large, multidimensional arrays and matrices along with a large collection
of high-level mathematical functions to operate on these arrays. NumPy
stands for Numerical Python. NumPy is a Python library used for working
with arrays. It also has functions for working in the domain of linear algebra,
Fourier transform, and matrices. The core functionality of NumPy is its "ND
array", for n-dimensional array, data structure. These arrays are stride views
on memory. In contrast to Python's built-in list data structure, these arrays
are homogeneously typed: all elements of a single array must be of the same
type. [14]
4.1.2 Implementation details of modules:
- Registration Module.
This Modules help to register the new user to the web application and also help to
store the user enter data into the PostgreSQL. In which it helps to give access to the
user into the web application. It also checks whether the user is already there or not
into the database so there will be no two named persons in the single web
application.
Operation provided by this model system are:
- Add_record ()
- check_record ()
- has_pass ()

26
- Login / Logout Module.
This Modules helps to login in or logout from the web application where you have
to enter the record you have entered in the registration form. If the enter record is
matched to the database, then it will lead the user to the home page of application
if not correct then it will be in the login page until and unless the enter data is
matched with the database record it will not redirect to the homepage of the
application. And, also the entered data will be stored in the session. The log out
will take you to the login page destroying the session that has been stored while
login the data.
Operational provided by this model system are:
- login_user()
- logout_user()
- session_user()
- destroy_session()
- check_hash_password()
- check_record()
- User management Module.
This Module helps for managing different users of the system by taking the secure
measure to protect data and also gives the access to edit their post, username,
password, and email which are all stored in PostgreSQL. Using different buttons
that have been coded with different queries and actions for the user to make them
easy.
Operation provided by this model system are:
- add_post()
- delete_post()
- update_post()
- update_email()
- update_pass()
- update_uname()

27
- Text analysis Module.
This Model is used to analyze all the text that a user has posted in the web
application where the only positive content is taken in the application. To share the
positivity toward the people using it. The module works into different techniques
that are listed below:
- Tokenization
Tokenization is the act of breaking up a sequence of strings into pieces
called tokens. Tokens can be individual words or even whole sentences. For
example: Liana had a great year in 2021. The tokenization of this sentence
is:
-Liana - had -a -great -year -in -2021
- Cleaning the data
Cleaning the data involves removing the special characters. So, after
cleaning the data we get, -Liana -had -a -great -year -in -2021
- Removing the stop words
Stop words are commonly used in Text Mining and Natural Language
Processing (NLP) to eliminate words that are so commonly used that they
carry very little useful information.
-Liana –
- Classification
Positive: +1
Negative: -1
Neutral: 0
- Apply supervised algorithm for classification
Supervised algorithm is a learning algorithm that maps an input to an output
based on example
input-output pairs. In simple terms, supervised learning means if this (input)
then that (output).
Liana: 0
great: 1

28
- Calculation
1+0 = 1
Polarity >0: positive
Polarity<0: negative
Figure 12: Token Analysis Module
- Database Module.
This Module will be implemented by an object database management system used
to store the persistence data. The database consists of the following:
User: User added to database with Unique id based on the role.
Post: Post added to the database with the user’s name to see who posted
the post.
Data Object:
U_id, Username, Full Name, Email, Password
Post_id, post, username

29
4.2 TESTING
4.2.1 Purpose of Testing:
The purpose of testing is to help in finalizing the software application or product against
business and user requirements. It is very important to have good test coverage in order
to test the software application completely and make it sure that it’s performing well as
per the specifications. Testing can be verification and validation or reliability
estimation. Some of the objectives of software testing are given below:
• To check whether software is built. It is as per the requirement or not.
• Finding defects from the software before customers find them out.
• Defects get a fix from the developer.
• Preventing defects.
• Gaining confidence about the level of quality.
4.2.2 Test case for Unit Testing:
A) Signup page:
Objectives To enter the record of the user for the login purpose.
Action The input section should be filled with the Full Name, User
Name, Email and the Password should be hidden.
Excepted Results To enter all the data correctly which stores the data into the
database and pressing the signup button should redirect to the
login page.
Actual Results All user data is inserted into the input field and all data is
stored into the database and the button redirects to the login
page.
Conclusion Test Successful.

30
Figure 13: Sign Up of the Page
Figure 14: Login Form Page of the System

31
B) Login Page:
Objectives To enter the record of the user to enter the main page of the
project.
Action Enter the user email and password, pressing the login button
leads to the main page.
Excepted Results To enter the Email and Password of the user and if the email
and password matched in the database then login to the main
page.
Actual Results The email and password are verified and entered into the main
page.
Figure 15: Login by User

32
Figure 16: User Page After Login into the System
C) Posting only the positive Content:
Objectives To enter the post which only takes the positive content.
Action Click on the post button on the top right lead to the boc to
enter the content from the user
Excepted Results While entering the content the post is only successful when
the content posted is positive.
Actual Results The post is stored into the database and the positive content
is shown to the users.

33
Figure 17: Posting the only positive Content (a)
Figure 18: Posting the only positive Content (b)

34
D) User Page:
Objectives To go to the user account page where it gives the details of
the post.
Action Clicking on the side navbar and going to the account page
Excepted Results To show the all the data of the user and the number of their
post
Actual Results Shows all the email, username and password from the
database.
Figure 19: User Page

35
E) Post Page:
Objectives To show the users posts
Action Clicking on the side navbar to go to post page
Excepted Results To show the users personal posts that are posted in social
media.
Actual Results Shows the post result from the database which the user can
delete and edit the post content.
Figure 20:Post Page of the System

36
F) Delete Post:
Objectives To delete the user post
Action Pressing the delete for deleting the post of the user.
Excepted Results To Delete the posted content form the user post.
Actual Results Deleted the post by pressing the delete button and also
deleted from the database.
Figure 21: Delete Post (a)

37
Figure 22: Delete Post (b)
G) Edit Post:
Objectives To edit the user post that has been posted.
Action Pressing the edit button to edit the content.
Excepted Results To appear the new model to edit the post.
Actual Results The edit button leads to the model pop up that helps to edit
and also gets edited on the database.

38
Figure 23: Edit Post (a)
Figure 24 :Edit Pos (b)t

39
Figure 25: Edit Post (c)
H) Edit User Name, Email and Password:
Objectives To edit the Email, Username and Password
Action Pressing the edit button mounted at side of every single div
Excepted Results To change the Username, Email and Password
Actual Results The Username, Email and Password is being updated and
also been updated in the database for the login purpose.

40
Figure 26: Edit Username (a)
Figure 27: Edit Username (b)

41
Figure 28: Edit Post page
Figure 29: Edit Detail Post

42
Figure 30: Successfully Edited
I) About page:
Objectives To show the about page of the project.
Action Clicking the side navbar to go to the about page.
Excepted Results To show the detail about the project why it is made by
clicking the side navbar.
Actual Results The about page is shown.

43
Figure 31: About System
J) Logout:
Objectives To get out of the web application
Action Clicking the logout on the side navbar.
Excepted Results To go to the login page while clicking the logout page.
Actual Results While pressing the button it leads the user to the login page
and also destroys all the sessions stored while processing.

44
Figure 32: Logout Page of the System
Figure 33: Back to Login Page after Logout

45
4.2.3 Test case for System Testing:
System testing is a process of testing the entire system that is fully functional, in order to
ensure the system is bound to all the requirements provided by the client in the form of the
functional specification or system specification documentation. In most cases, it is done
next to the Integration testing, as this testing should be covering the end-to-end system’s
actual routine. So, the System Testing is divided into two testing that is:
- Alpha Testing
Alpha testing is the final stage of testing performed by your QA team to check that
your application is ready for release outside your company. The testing is
coordinated in-house, structured and is usually done by your own test team. Alpha
testing is predominantly about ensuring bug-free functionality.
This testing is done very carefully for the bug-free. While doing this we found
different bugs and some of the bugs have been solved. A few bugs are still needed
to be fixed. The bugs that are there like (popup bugs and posts that are not posted
even though the data is positive.). There are a few bugs that we are working to
solve. But the bugs do not affect the performance of the system a little bit. so, we
can say that it is ready to be released in the real world.
- Beta Testing
Beta testing involves releasing the software to a limited number of real users. They
are free to use it as they want. In other words, this testing is unstructured. However,
the users are encouraged to give feedback about how the application performs.
Usually, you will also monitor how the backend is performing during these tests.
Beta testing is more focused on performance and scalability.
So, for the beta testing we have given access to the beta project to a few friends for
a week then after a week the feedback is taken from the users. The feedback was
the UI and the color coordination is very well and the working process is smooth.
And, also the content they have been getting is all positive meaning the aim of the
project works greatly. The only drawback is that the project has the bugs that while
posting the content even the positive content the data is not taken by the application.
But, after solving the bugs it is a very good application for positive content which
is perfect for the real-world project.

46
CHAPTER 5
CONCLUSION AND RECOMMENDATIONS
5.1 CONCLUSION
To Conclude, Eywry is a simply a web-based application in which it helps to share the
positive content among the people connected to it. The Eywry is simply a web-based
framework developed on the python and flask framework. It works using the data training
which trains the data which are listed in the database and after the data is trained the user
input the post and according to the data the post is taken using the data polarity if the post
content the polarity of 1 then it is been posted but if the post content the polarity of 0 then
the post will be dumped. By doing this I have achieved and learned different thing while
doing this project and had fun doing and working for the project.
5.2 LESSON LEARNT/OUTCOME
While making this project we have learnt many things. And they are listed down below:
- Learn about the flask and python.
- Learn how to train the data using unsupervised learning.
- Learn to solve the errors found in the project.
- Learn to communicate with the team.
- Learn to make a workable real time project.
5.3 FUTURE RECOMMENDATIONS
We have got many things that we want to do in the coming days, so some of these are listed
below:
- We will add the training of data in the images as well as the videos.
- We will add more data sets so the analysis could get much more accurate.
- We will add the optional account to switch to an anonymous account and the
identification account.
- We will try to add more bug free and error free applications.

47
References
[1] M. M. D. a. M. K. Abdul-Mageed, Subjectivity and sentiment analysis of modern,
2011.
[2] Lexalytics, "Lexalytics," Lexalytics, 08 10 2009. [Online]. Available:
https://www.lexalytics.com/technology/sentiment-analysis/.
[3] S. B. R. Das, " Real-time sentiment analysis of twitter streaming data," Compute, 02
september 2018. [Online].
[4] D. O. T. a. A. R. Davidov, t. Enhanced sentiment learning using twitter hashtags and
smileys., 2010.
[5] M. Gamon, Sentiment classification on customer feedback data: noisy data, large
feature vectors, and the role of linguistic analysis., In Proceedings of Intl. Conf. on
Computational Linguistics, 2004.
[6] S. Gupta, Sentiment Analysis for Classifying Sentiment of Movie Reviews, 2007.
[7] Moskowitz, "Sanford Moskowitz," 19 12 2013. [Online]. Available:
https://silverskylabs.github.io/yakhak/. [Accessed 30 09 2021].
[8] S. a. V. N. Dasgupta, a semi-supervised approach to automatic sentiment
classification, 2009.
[9] R. Kumar Behera, S. Kumar Rath, S. Misra, R. Damaševiˇcius and Maskeli,
"Distributed centrality analysis of social network data using MapReduce.
Algorithms," 22 june 2019. [Online].
[10] N. S. Chauhan, "KD nuggets," 15 06 2020. [Online]. Available:
https://www.kdnuggets.com/2020/06/naive-bayes-algorithm-everything.html.
[Accessed 18 12 2021].
[11] Forester, "Naive Bayes Classifier," machine learning knowledge,vol. ii, p. 180, 2008.
[12] B. Momjian, "PostgreSQL," PostgreSQL: Introduction and Concepts, vol. 1, no. 10,
p. 462, 2005.
[13] M. a. Kyrin’s, HTML, CSS, and JavaScript All in One, pristone, 2000.
[14] E. Matthes, "Python Crash Course, 2nd Edition," A Hands-On, Project-Based
Introduction to Programming, vol. ii, no. 3, p. 544, 2019.
[15] Z. Luo T Chen, "Sentiment analysis. In: Trustbased Collective View Prediction,"
Springer, New York, 2013.
[16] M. Vohra and J. Teraiya, "Applications and challenges for sentiment analysis,"
English report technology, 2013.
[17] Y. Yu, W. Duan and Q. Cao, "The impact of social and conventional media on firm
equity value a sentiment analysis approach," 28 december 2013. [Online].

48
[18] P. G. Hu, "An ensemble deep learning model for drug abuse detection in sparse
twitter-sphere," 18 july 2016. [Online]. [Accessed 14 december 2021].
[19] K. Mouthami and Devi, "Sentiment analysis," 23 january 2013. [Online]. [Accessed
12 december 2021].
[20] Z. a. K. H. B. Ghahramani, Advances in Neural Information Processing Systems,
2006.
[21] D. D. W. a. J. C. Bollegala, Using multiple sources to construct a sentiment sensitive
thesaurus for cross-domain sentiment classification, 2011.
[22] H. V. M. a. M. D. Cui, Comparative experiments on sentiment classification for
online product reviews., 2006.

Project documentaion sample.docx

Recommended

Recommended

More Related Content

What's hot

What's hot (20)

Similar to Project documentaion sample.docx

Similar to Project documentaion sample.docx (20)

Recently uploaded

Recently uploaded (20)

Project documentaion sample.docx