PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS GUJARAT TECHNOLOGICAL UNIVERSITY

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
GUJARAT TECHNOLOGICAL UNIVERSITY, AHMEDABAD
S.P.B. PATEL ENGINEERING COLLEGE, LINCH
A
PROJECT REPORT
ON
“Social media sentiment analysis”

SUBMITTED BY:
Kaushik Mandal – IT (150390116006)
Prashant Thevar – IT (150390116017)
Pinakin Prabhakar – CE (150390107012)
Sourabh Rupani – CE (150390107016)

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!


order now

TEAM ID: 13937

IN FULFILLMENT FOR THE AWARD OF THE DEGREE
OF
BACHELOR OF ENGINEERING
IN
COMPUTER ENGINEERING /
INFORMATION TECHNOLOGY

JULY – OCTOBER 2018

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 2

GUJARAT TECHNOLOGICAL UNIVERSITY, AHMEDABAD
S.P.B. PATEL ENGINEERING COLLEGE
SAFFRONY INSTITUTE OF TECHNOLOGY

CERTIFICATE

This is to certify that the project entitled Social Media Sentiment Analysis is a bonafide report
of the work carried out by Kaushik Mandal (150390116006) under the guidance of Prof.
Manan Thakkar for the successful completion of the project, Information Technology /
Computer Engineering at Saffrony Institute of Technology – Linch, Mehsana, Gujarat.

To the best of our knowledge and belief, this work embodies the work of candidate
herself/himself, has duly been completed, fulfills the requirement of the ordinance relating to
the completion of the project and is up to the standard in respect of content, presentation, and
language for being referred to the examiner.

Internal Guide HOD CE-IT
Prof. Manan Thakkar Prof. Akshay Kansara
CE/IT Dept. CE/IT Dept.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 3

GUJARAT TECHNOLOGICAL UNIVERSITY, AHMEDABAD
S.P.B. PATEL ENGINEERING COLLEGE
SAFFRONY INSTITUTE OF TECHNOLOGY

CERTIFICATE

This is to certify that the project entitled Social Media Sentiment Analysis is a bonafide report
of the work carried out by Prashant Thevar (150390116017) under the guidance of Prof.
Manan Thakkar for the successful completion of the project, Information Technology /
Computer Engineering at Saffrony Institute of Technology – Linch, Mehsana, Gujarat.

To the best of our knowledge and belief, this work embodies the work of candidate
herself/himself, has duly been completed, fulfills the requirement of the ordinance relating to
the completion of the project and is up to the standard in respect of content, presentation, and
language for being referred to the examiner.

Internal Guide HOD CE-IT
Prof. Manan Thakkar Prof. Akshay Kansara
CE/IT Dept. CE/IT Dept.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 4

GUJARAT TECHNOLOGICAL UNIVERSITY, AHMEDABAD
S.P.B. PATEL ENGINEERING COLLEGE
SAFFRONY INSTITUTE OF TECHNOLOGY

CERTIFICATE

This is to certify that the project entitled Social Media Sentiment Analysis is a bonafide report
of the work carried out by Pinakin Prabhakar (150390107012) under the guidance of Prof.
Manan Thakkar for the successful completion of the project, Information Technology /
Computer Engineering at Saffrony Institute of Technology – Linch, Mehsana, Gujarat.

To the best of our knowledge and belief, this work embodies the work of candidate
herself/himself, has duly been completed, fulfills the requirement of the ordinance relating to
the completion of the project and is up to the standard in respect of content, presentation, and
language for being referred to the examiner.

Internal Guide HOD CE-IT
Prof. Manan Thakkar Prof. Akshay Kansara
CE/IT Dept. CE/IT Dept.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 5

GUJARAT TECHNOLOGICAL UNIVERSITY, AHMEDABAD
S.P.B. PATEL ENGINEERING COLLEGE
SAFFRONY INSTITUTE OF TECHNOLOGY

CERTIFICATE

This is to certify that the project entitled Social Media Sentiment Analysis is a bonafide report
of the work carried out by Sourabh Rupani (150390107016) under the guidance of Prof.
Manan Thakkar for the successful completion of the project, Information Technology /
Computer Engineering at Saffrony Institute of Technology – Linch, Mehsana, Gujarat.

To the best of our knowledge and belief, this work embodies the work of candidate
herself/himself, has duly been completed, fulfills the requirement of the ordinance relating to
the completion of the project and is up to the standard in respect of content, presentation, and
language for being referred to the examiner.

Internal Guide HOD CE-IT
Prof. Manan Thakkar Prof. Akshay Kansara
CE/IT Dept. CE/IT Dept.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 6

ACKNOWLEDGEMENT

We are heartily thankful to our Prof. Manan Thakkar, whose encouragement, supervision
and support from the preliminary to the concluding level enabled us to develop an
understanding of the subject. At the end, we offer my regards and to all of those who
supported us in any respect during the completion of the project and to our college for
providing resources & materials.

We express our gratitude to Prof. Akshay Kansara HOD C.E/I.T for constant
encouragement, cooperation, and support and also thankful to all people who have
contributed in their own way of making this project successful.

We take this opportunity to thank all our classmates for their company during the coursework
and for useful discussion we had with them. Under these responsible and talented
personalities, we were efficiently able to undertake this project.

Regards,

Kaushik Mandal (150390116006)
Prashant Thevar (150390116017)
Pinakin Prabhakar (150390107012)
Sourabh Rupani (150390107016)

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 7

ABSTRACT

Analysis of open data from web-based life could yield intriguing outcomes and
bits of knowledge into the universe of general feelings about any item, benefit or
identity. Social Network Data is a standout amongst the best and exact pointers
of open assessment. The blast of Web 2.0 has prompted expanded movement in
Podcasting, Blogging, Labeling, Adding to RSS, Social Bookmarking, and
Informal communication. Thus, there has been an emission of enthusiasm for individuals to
mine these huge assets of information for sentiments. Feeling Examination or Assessment
Mining is the computational treatment of assessments, notions and subjectivity of
content. In this paper we will examine a technique which permits use and
elucidation of twitter information to decide general assessments.

Our goal is to build a sentiment-based analysis system which is helpful in analyzing the
sentiments on the basis of the response by the user. For this, we will need the implementation
of Naïve Bayes Algorithm, Multinomial Naive Bayes Algorithm, Logistic Regression
Algorithm, Stochastic Gradient Descent (SGD) Algorithm, and NuSVM Algorithm. These
algorithms help in performing the analysis of the text based on the features of the particular
system.

Keywords: Data mining, Natural language processing, Sentiwordnet, Naïve Bayes

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 8

TABLE OF CONTENTS
1. Introduction…………………………………………………..………….………………….. 10
1.1 Introduction………..………………………………………………………………………. 10
1.2 Limitation of existing system………………………………………………………. 10
1.3 Objective of the New System..…………………….………………..…………………. 11
1.4 Problem Definition…..…………………………………………………………………. 11
1.5 Prior Art Search (PAS)……………………….……………………………….…… 12
1.6 Plan of work.………………………………..……………………………………… 17
1.7 Materials / Tools required …………………………………………………………….… 17
2. Project Management………………………..……………………………………………. 20
2.1 Milestones And Deliverables………………..……………….……………………. 20
2.2 Risk Management………………………………………………………….………..20
2.2.1 Project Risk………………………………………..……………………………. 21
2.2.2 Risk Planning…………………………………………………………………… 22
3. System Analysis and Requirement……………………….…………………………….. 23
3.1 System Feasibility……………………………………………………………………23
3.2 Requirements of System………………………………..……………………………24
3.3 Project Requirements………………………………………………….…………… 24
3.3.1 Functional requirements…………………………………………………..………24
3.3.2 Non-Functional requirements………………………………………..…………… 24
3.4 Design constraints………………………………………………………..………… 25
4. System Design…………………………………………………………………………… 26
4.1 System Flow Diagram….…………………………………………………………… 26
4.2 Use-Case Diagram….………………………………………………………………. 28
4.3 Data Flow Diagram..……………………………………………………………….. 29
4.4 Sequence Diagram..………………………………………………………………….30
4.5 Activity Diagram……………………………………………………………………. 31
4.6 Flow Chart..…………………………………………………………………………………32
5. Testing…………………………………………………………………………………… 33
6.1 Testing Overview…………………………………………………………………… 33
6.2 Testing Methods……………………………………………………………………. 34

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 9

6. Appendix………………………………………………………………………………………….. 37
7. References………………………………………………………………………………………….41

List of figures
Fig 1.1: Android cell phone…………………………………………………………………. 18
Fig 1.2: Android studio……………………………………………………………………… 19
Fig 1.3: Python Software Foundation (PSF)…………………………………………………. 19
Fig 1.4: Gantt chart……………………………………………………………………….… 20
Fig. 4.1.1 System Flow Diagram…………………………………………………………… 26
Fig. 4.1.2 System Flow Diagram…………………………………………………………… 27
Fig. 4.2 Use-Case Diagram…..………………………………………………………………. 28
Fig. 4.3 Data Flow Diagram..………………………………………………………………. 29
Fig. 4.4 Sequence diagram….………………………………………………………………. 30
Fig. 4.5 Activity Diagram……………………………………………………………….…… 31
Fig. 4.6 Flow Chart………..…………………………………………………………….…… 32
Fig.5.1 Phases of Testing…………………………………………………………………… 34
Fig.6.1 AEIOU CANVAS………………………………………………………………….. 37
Fig.6.2 EMPATHY CANVAS…………………………………………………………………………………. 38
Fig.6.3 IDEATION CANVAS………………………………………………………………39
Fig.6.4 PRODUCT DEVELOPMENT CANVAS…………………………………………. 40

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 10

CHAPTER-1
INTRODUCTION

1.1 Introduction
We will perform sentiment analysis on tweets, product/movie/food reviews, etc. to extract
what feature of the particular entity that makes people feel good or bad about. We analyze the
written reviews of users and try to find the precise sentiment of different aspects of the
entity.

For example, many users recommended the camera quality of a certain mobile phone, even
though the overall ratings are not good, then we can analyse user’s opinion on its camera
feature from the written reviews in order to help the other users as well as the company. Thus,
it will become easier for the users to identify the product, along with their needs.

1.2 Limitation of Existing System
• The existing system does not perform sentiment analysis on a perfect basis as the
current system focuses on an overall analysis of the overall review.
• Some of the features that may be good as compared to other features get neglected
while performing analysis for the system as a whole and so the resulting outputs or
reviews obtained may not be appropriate.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 11

1.3 Objective of the New System
• To perform sentiment analysis in such a manner that not only the product or system
gets reviewed as a whole, but also the individual feature qualities get highlighted.
• Because if product is not good that doesn’t mean all of its features aren’t good, and
vice versa.

• Yin Yang is the perfect example.

1.4 Problem Defintion
Sentiment analysis is yet not a relevant solution to get analytical summary of the
sentiment of user reviews.

? Creator will only know about overall sentiments of his/her product. He/she won’t
be able to figure out exactly where the improvements are needed and exactly what
makes people feel good about in his/her product.
? Same goes for buyers.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 12

1.5 Prior Art Search

1.5.1. Self-learning system for determining the sentiment conveyed by an
input text.

Inventors: Vinay Gururaja Rao, Ankit Patil, Santhosh Saurabh, Pooviah Ballachanda Ayappa

Application number: US20150199609A1

Publication Date: 07/16/2015

Summary:

A self learning framework and a strategy for breaking down the opinions passed on by an info
content have been unveiled. The framework incorporates a generator that produces an
underlying preparing set containing a majority of words connected to comparing notions. The
words and comparing opinions are put away in a store. A lead based classifier isolates the info
content into individual words, and contrasts the words and the sections in the storehouse, and
in this way decides a first score comparing to the information content. The information content
is likewise given to a machine-learning based classifier that produces a majority of highlights
relating to the info content and accordingly creates a second score comparing to the info
content. The principal score and the second score are additionally collected by a gathering
classifier which additionally creates a grouping score demonstrative of the notion passed on
by the information content.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 13

1.5.2 Sentiment and Influence Analysis of Twitter Tweets

Inventors: Duong-Van Minh

Application number: US20130103667A1

Publication Date: 04/25/2013

Summary:

The present development is coordinated to a framework, strategy, and article of fabricate that
utilizes a feeling motor for leading slant and impact investigation of different kinds of
messages from the web based life hosts or sites to separate suppositions on various
classifications, which incorporates administrations, items or lodgings, and others, by and large
alluded to as “the catchphrase item”. The supposition motor incorporates a feeling module
designed to assemble conclusions or decide notion communicated in records, a slithering
module arranged to servers of informal organization sites to get something like a subset of the
reports or assessments from online life sites, a watchword module designed to remove
catchphrases from archives, a sifting module designed to channel watchwords and reports, and
a characterization module designed to group reports, sentences, and additionally watchwords,
an extremity forecast module designed to anticipate the extremity of an assumption sentence,
and a web based life net advertiser score designed to compute a faithfulness metric of clients
from internet based life sites, and a message examination module arranged to direct
investigation of a message from host web based life destinations, gatherings, web journals and
item/specialist organizations. The message examination module incorporates breaking down
message from other host online life destinations.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 14

1.5.3 Sentiment analysis

Inventors: Mihir Parikh, Robert M. Fabricant, Ed Hicks

Application number: US20120191730A1

Publication Date: 12/08/2015

Summary:

Information is gotten from various information sources. No less than one of the information
sources is a functioning sound or video correspondence. The got information is investigated
by extricating examples of a catchphrase from the got information and examining logical
information close to the watchword. Notion about the separated catchphrase is checked
dependent on the relevant information. The got opinion information from the numerous
information sources is accumulated, and a collected perspective of the determined feeling
information is introduced.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 15

1.5.4 Sentiment analysis from social media content

Inventors: Minh Duong-Van

Application number: US20120101808A1

Publication Date: 12/01/2015

Summary:

Strategies and frameworks for separating and investigating user-generated content (UGC) with
the end goal to give conclusion bearing data concerning distinctive classes of an item. Gathered
Web pages are analyzed for watchwords to distinguish classifications to which they relate.
Conclusion bearing data in regards to those classifications is then removed and examined to
decide its introduction and, alternatively, its quality. The subsequent slant judgments can be
accumulated over various item surveys and such to build up a supposition outline, which can
be accounted for and utilized as the reason for promoting, advertising and obtaining choices,
among others.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 16

1.5.5 Sentiment prediction from textual data

Inventors: Jerome Bellegarda

Application number: US20110112825A1

Publication Date: 03/25/2014

Summary:

A semantically sorted out area space is made from a preparation corpus. Emotional information
are mapped onto the area space to create full of feeling grapples for the space. A feeling related
with an information content is resolved based the emotional stays. A discourse yield might be
created from the info content dependent on the decided estimation.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 17

1.6 Plan of work

Name Social Media Sentiment Analysis

Project Objective • GUI design for application
• Digital menu for pre-ordering
• Table Booking system
• Chabot for queries and to help customers
Project Execution Model Spiral model
Internal Guide Prof. Manan Thakkar
Team Size 4
Duration 8 months

Table 1.1: Plan of work

1.7 Materials / Tools Required

HARDWARE REQUIREMENTS

? Mobile Cell Phone
? Specifications
• Devices running Android 5.1 or above.
• At least 1 GB RAM Storage capacity.
• Internet connectivity.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 18

Fig 1.1: Android cell phone

? For the development of our application
1. OS: Windows 8, 10, 64-bit versions only
2. CPU: i7 7th Generation.
3. GPU: Graphics card with DX10 (shader model 4.0) capabilities.

? For running our application
1. Device: Android mobile cell phone
2. Android: OS 5.1 or above

SOFTWARE REQUIREMENTS

1. Android Studio
Android Studio is the formally integrated development environment (IDE) for Google’s
Android working framework, based on JetBrains’ IntelliJ IDEA programming and planned
particularly for Android development. It is accessible for download on Windows, macOS and
Linux based working frameworks. It is a trade for the Eclipse Android Development Tools
(ADT) as essential IDE for local Android application improvement.

2. Features of Android Studio
The following features are provided in the current stable version:

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 19

• Gradle-based build support
• Android-particular refactoring and convenient solutions
• Lint apparatuses to get the execution, ease of use, form similarity, and different issues
• ProGuard integration and app-signing capabilities
• Template-based wizards to make basic Android plans and parts
• A rich design editorial manager that enables clients to move UI segments, alternative
to see formats on various screen arrangements
• Support for building Android Wear applications
• Built-in help for Google Cloud Platform, empowering combination with Firebase
Cloud Messaging (Earlier ‘Google Cloud Messaging’) and Google App Engine17
• Android Virtual Device (Emulator) to run and troubleshoot applications in the Android
studio.

Fig 1.2: Android studio
3. Python Software Foundation (PSF)
The Python Software Foundation (PSF) is a not-for-profit association gave to the Python
programming dialect, propelled on March 6, 2001. The mission of the foundation is to foster
the development of the Python community and is responsible for various processes within the
Python community, including developing the core Python distribution, managing intellectual
rights, and developer conferences including PyCon, and raising funds.

Fig 1.3: Python Software Foundation (PSF)

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 20

CHAPTER-2
PROJECT MANAGEMENT

2.1 Project Milestones and Deliverables

Fig 1.4: Gantt chart

2.2 Risk Management
A risk is defined as the possibility of any negative occurrence that may happen due to external
or internal factors, and that may be mitigated through preventive actions. All projects are
subject to risks. In fact, there is an infinite number of things that might prevent you from
achieving your goals when working on a project. Risk management minimizes those threats
that could cause project failure and allows you to stay in control of your project’s schedule,
budget and quality requirements.
? Identification: Detect risks that might prevent you from achieving your project’s goals.
? Analysis: Determine what risks are the most dangerous.
? Planning: Plan for the most dangerous risks.
? Monitoring and control: Maintain the project’s plan and continually identify risks.
Risk management is concerned with identifying risks and drawing up plans to minimize their
effect on a project. A risk is a probability that some adverse circumstance will occur.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 21

2.2.1 Project Risks

? Customer Characteristics (CC):
• Given that the project has to have a good playability besides the technical attributes,
end-users’ dissatisfaction from the system by demanding enhancements of the other
properties which are out of project scope forces reassessment of project objectives
and scope, thus disrupting project layout.

? Product Parameters(PP):
• Given that the strict deadlines, underestimated project size will increase total
project completion time, thus making it impossible to meet the deadlines.
• Given that components are imported to satisfy the functionality of a module, any
incapability of a component leads to either extension of the component (if possible),
or substituting the component with another, in any case resulting in an extra non-
scheduled effort.
• Given that many components (e.g. engines) are integrated to realize the project, a
possible disintegrative stemming from any component may lead to an unexpected
gap in design, thus introduce the reassessment of the design with a new component.
• Given that the task distribution is based on major roles, the discovery of too many
minor roles that have been previously ignored causes an extra burden on the team
members.
• Lacking component integration.
• A wrong estimate of hardware.

? Development Process(DP):
• Given that the desired level of software quality is to be met, the deficiency of
software quality assurance results of the degrading quality of the product.
• Given that the process relies on the validity of the modules as well as the integrity
of all, the absence of a detailed, systematic bottom-up testing approach makes it
impossible to recover from the defects revealed too late.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 22

2.2.2 Risk Planning
Risk planning can be basically said as a technique which any software developer follows to
avoid risk in his/her project. It can be the preventive measures or measures taken to come out
of the risk safely.

The most and important thing is always team bonding. Regular meetings should be conducted
so the team members get to know each other properly and they can work in coordination. The
work of the team must be divided in such a way that the teammates are always familiar with
each other’s work and hence even if one of the members of the team isn’t present then the team
can work properly.

In our application, the most important stuff is mentors who would be guiding the students.
However, for this, we need to select the appropriate mentor such that the student won’t face
any problem in sharing their experiences with them and this would be the most challenging
task for us.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 23

CHAPTER-3
SYSTEM ANALYSIS ; REQUIREMENTS

3.1 System Feasibility

A study of resource availability that may affect the ability to achieve an acceptable system.
This evaluation determines whether the technology needed for the proposed system is available
or not. Since we are developing an application in Android Studio, so this project is very
difficult to develop without enough knowledge for running the application as well as testing it.
Economic justification includes a broad range of concerns that include a cost-benefit analysis.
In this we weight the cost and the benefits associated with the candidate system and if it suits
the basic purpose of the organization.

? Steps in feasibility analysis:

Eight steps involved in the feasibility analysis are:
• Form a project team and appoint a project leader.
• Prepare system flowcharts.
• Enumerate potential proposed system.
• Define and identify characteristics of a proposed system.
• Determine and evaluate performance and cost-effective of each proposed system.
• Weight system the performance and cost data.
• Select the best-proposed system.
• Prepare and report final project directive to management.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 24

3.2 Requirement of System

? Android Studio
? Python Software Foundation

3.3 Project Requirements

3.3.1 Functional Requirements
Functional requirements deal with what the system should do or provide for users. They
include a description of the required functions, outlines of associated reports or online queries,
and details of data to be held in the system.

• Framework ought to have the capacity to process new tweets put away in database after
recovery
• Framework ought to have the capacity to examine information and characterize each
tweet extremity
• Algorithm should give accuracy as high as possible.
• User will be able to download the analysis report in various file formats.
• User will be able to access his/her search history.

3.3.2 Non-functional Requirements
Non-functional requirements detail constraints, targets or control mechanisms for the new
system. They describe how, how well or to what standard a function should be provided:

• User-friendly
• System should provide better accuracy
• To perform with efficient throughput ; response time.
• Design should be mobile responsive.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 25

3.4 Design Constraints

1. Time Constraints:
• There exist strict deadlines for each phase of the process, so the constraint of meeting
the deadlines is of utmost concern.

2. Tool Constraints:
• Using Graphics and AI Engines leads to limitations within the corresponding domain
according to the implementation of functionalities. While engines reduce the burden of
low-level programming, they introduce constraints to the capabilities of the project.

3. Personnel Constraints:
• The project is subject to balanced distribution of the limited workforce.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 26

CHAPTER-4
SYSTEM DESIGN

4.1 System Flow Diagram

Fig. 4.1.1 System Flow Diagram

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 27

Fig. 4.1.2 System Flow Diagram

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 28

4.2 Use-Case Diagram

Fig. 4.2 Use-Case Diagram

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 29

4.3 Data Flow Diagram

Fig. 4.3 Data Flow diagram

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 30

4.4 Sequence Diagram

Fig. 4.4 Sequence Diagram

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 31

4.5 Activity Diagram

Fig. 4.5 Activity Diagram

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 32

4.6 Flow Chart

Fig. 4.7 Flow Chart

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 33

CHAPTER-5
TESTING

Software testing is an investigation conducted to provide stakeholders with information about
the quality of the product or service under test. Software testing can also provide an objective,
independent view of the software to allow the business to appreciate and understand the risks
of software implementation. Test techniques include, but are not limited to the process of
executing a program or application with the intent of finding software bugs (errors or other
defects).

Software testing can be stated as the process of validating and verifying that a computer
program/application/product:
• meets the requirements that guided its design and development,
• works as expected,
• can be implemented with the same characteristics,
• Satisfies the needs of stakeholders.

Software testing, depending on the testing method employed, can be implemented at any time
in the software development process. Traditionally most of the test effort occurs after the
requirements have been defined and the coding process has been completed, but in the agile
approaches, most of the test effort is on-going. As such, the methodology of the test is governed
by the chosen software development methodology.

5.1 TESTING OVERVIEW:
A primary purpose of testing is to detect software failures so that defects may be discovered
and corrected. Testing cannot establish that a product functions properly under all conditions
but can only establish that it does not function properly under specific conditions. The scope
of software testing often includes an examination of code as well as the execution of that code
in various environments and conditions as well as examining the aspects of code: does it do
what it is supposed to do and do what it needs to do. In the current culture of software

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 34

development, a testing organization may be separate from the development team. There are
various roles for testing team members. Information derived from software testing may be used
to correct the process by which software is developed.
Every software product has a target audience. For example, the audience for video game
software is completely different from banking software. Therefore, when an organization
develops or otherwise invests in a software product, it can assess whether the software product
will be acceptable to its end users, its target audience, its purchasers and other stakeholders.
Software testing is the process of attempting to make this assessment.

Fig.5.1 Phases of Testing

5.2 TESTING METHODS
1. STATIC VS. DYNAMIC TESTING
• There are many approaches to software testing. Reviews, walkthroughs, or inspections
are referred to as static testing, whereas actually executing programmed code with a
given set of test cases is referred to as dynamic testing. Static testing is often implicit,
as proofreading, plus when programming tools/text editors check source code structure
or compilers (pre-compilers) check syntax and data flow as static program analysis.
Dynamic testing takes place when the program itself is run. Dynamic testing may begin
before the program is 100% complete in order to test particular sections of code and

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 35

are applied to discrete functions or modules. Typical techniques for this are either using
stubs/drivers or execution from a debugger environment.
• Static testing involves verification, whereas dynamic testing involves validation.
Together they help improve software quality. Among the techniques for static analysis,
mutation can be used to ensure the test-cases will detect errors which are introduced by
mutating the source code.
2. WHITE-BOX TESTING
• White-box testing (also known as clear box testing, glass box testing, and transparent
box testing, and structural testing) tests internal structures or workings of a program,
as opposed to the functionality exposed to the end-user. In white-box testing, an internal
perspective of the system, as well as programming skills, are used to design test cases.
The tester chooses inputs to exercise paths through the code and determine the
appropriate outputs. This is analogous to testing nodes in a circuit, e.g. in-circuit testing
(ICT).
• While white-box testing can be applied at the unit, integration and system levels of the
software testing process, it is usually done at the unit level. It can test paths within a
unit, paths between units during integration, and between subsystems during a system–
level test. Though this method of test design can uncover many errors or problems, it
might not detect unimplemented parts of the specification or missing requirements.
3. BLACK-BOX TESTING
• Black-box testing treats the software as a “black box”, examining functionality without
any knowledge of internal implementation. The testers are only aware of what the
software is supposed to do, not how it does it. Black-box testing methods include
equivalence partitioning, boundary value analysis, all-pairs testing, state transition
tables, decision table testing, fuzz testing, model-based testing, use case testing,
exploratory testing, and specification-based testing.
• One advantage of the black box technique is that no programming knowledge is
required. Whatever biases the programmers may have had, the tester likely has a
different set and may emphasize different areas of functionality. On the other hand,
black-box testing has been said to be “like a walk in a dark labyrinth without a
flashlight.” Because they do not examine the source code, there are situations when a

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 36

tester writes many test cases to check something that could have been tested by only
one test case or leaves some parts of the program untested.
• This method of test can be applied to all levels of software testing: unit, integration,
system, and acceptance. It typically comprises most if not all testing at higher levels,
but can also dominate unit testing as well.
4. VISUAL TESTING
• The aim of visual testing is to provide developers with the ability to examine what was
happening at the point of software failure by presenting the data in such a way that the
developer can easily find the information he or she requires, and the information is
expressed clearly.
• Visual testing provides a number of advantages. The quality of communication is
increased dramatically because testers can show the problem (and the events leading
up to it) to the developer as opposed to just describing it and the need to replicate test
failures will cease to exist in many cases. The developer will have all the evidence he
or she requires of a test failure and can instead focus on the cause of the fault and how
it should be fixed.
• Visual testing is particularly well-suited for environments that deploy agile methods in
their development of software since agile methods require greater communication
between testers and developers and collaboration within small teams.
5. GREY-BOX TESTING
• Grey-box testing (American spelling: grey-box testing) involves having knowledge of
internal data structures and algorithms for purposes of designing tests while executing
those tests at the user, or black-box level. The tester is not required to have full access
to the software’s source code. Manipulating input data and formatting output does not
qualify as grey-box because the input and output are clearly outside of the “black box”
that we are calling the system under test. This distinction is particularly important when
conducting integration testing between two modules of code written by two different
developers, where only the interfaces are exposed for a test.

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 37

6. APPENDIX

6.1 AEIOU CANVAS

Fig.6.1 AEIOU CANVAS

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 38

6.2 EMPATHY CANVAS

Fig.6.2 EMPATHY CANVAS

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 39

6.3 IDEATION CANVAS

Fig.6.3 IDEATION CANVAS

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 40

6.4 PRODUCT DEVELOPMENT CANVAS

Fig.6.4 PRODUCT DEVELOPMENT CANVAS

PROJECT-I SOCIAL MEDIA SENTIMENT ANALYSIS
SAFFRONY INSTITUTE OF TECHNOLOGY Page 41

7. REFERENCES

1 https://www.python.org/

2 http://www.nlp.com/

3 https://developer.android.com/studio/

4 https://www.nltk.org/

https://patents.google.com/patent/US20150199609A1/en?oq=US20150199609A1
https://patents.google.com/patent/US20130103667A1/en?oq=US20130103667A1
https://patents.google.com/patent/US20120191730A1/en?oq=US20120191730A1
https://patents.google.com/patent/US20120101808A1/en?oq=US20120101808A1
https://patents.google.com/patent/US20110112825A1/en?oq=US20110112825A1

x

Hi!
I'm Heidi!

Would you like to get a custom essay? How about receiving a customized one?

Check it out